Güvenlik okumaları

Yapay zeka güvenliği üzerine öne çıkan arXiv makaleleri ve güvenlik araştırma bloglarından teknik yazılar.

Makale Konu
Explaining and Harnessing Adversarial Examples I. Goodfellow, Jonathon Shlens, C. Szegedy
Adversarial örnekler ve sağlamlık 2014 23597 150.8×
Intriguing properties of neural networks C. Szegedy, W. Zaremba, I. Sutskever vd.
Adversarial örnekler ve sağlamlık 2013 17251 101.7×
Towards Deep Learning Models Resistant to Adversarial Attacks A. Ma̧dry, Aleksandar Makelov, Ludwig Schmidt vd.
Adversarial örnekler ve sağlamlık 2017 16053 6.2×
Towards Deep Neural Network Architectures Robust to Adversarial Examples Shi-Xiang Gu, Luca Rigazio
Adversarial örnekler ve sağlamlık 2014 900 5.7×
Towards Evaluating the Robustness of Neural Networks Nicholas Carlini, D. Wagner
Adversarial örnekler ve sağlamlık 2016 10429 4.6×
Poisoning behavioral malware clustering B. Biggio, K. Rieck, D. Ariu vd.
Zehirleme ve arka kapılar 2014 158 4.3×
Extracting Training Data from Large Language Models Nicholas Carlini, Florian Tramèr, Eric Wallace vd.
Gizlilik ve model çalma 2020 3525 4×
Deep Learning with Differential Privacy Martín Abadi, Andy Chu, I. Goodfellow vd.
Gizlilik ve model çalma 2016 8722 3.9×
Practical Black-Box Attacks against Machine Learning Nicolas Papernot, P. McDaniel, I. Goodfellow vd.
Adversarial örnekler ve sağlamlık 2016 4254 3.9×
Universal and Transferable Adversarial Attacks on Aligned Language Models Andy Zou, Zifan Wang, Nicholas Carlini vd.
Jailbreak ve red teaming 2023 3995 3.9×
Adversarial examples in the physical world Alexey Kurakin, I. Goodfellow, Samy Bengio
Adversarial örnekler ve sağlamlık 2016 6987 3.1×
Red Teaming Language Models with Language Models Ethan Perez, Saffron Huang, Francis Song vd.
Jailbreak ve red teaming 2022 1417 2.4×
Membership Inference Attacks Against Machine Learning Models R. Shokri, M. Stronati, Cong-Zheng Song vd.
Gizlilik ve model çalma 2016 5849 2.3×
Membership Inference Attacks From First Principles Nicholas Carlini, Steve Chien, Milad Nasr vd.
Gizlilik ve model çalma 2021 1337 2.3×
Jailbroken: How Does LLM Safety Training Fail? Alexander Wei, Nika Haghtalab, Jacob Steinhardt
Jailbreak ve red teaming 2023 2331 2.2×
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Kai Greshake, Sahar Abdelnabi, Shailesh Mishra vd.
Prompt injection ve agent güvenliği 2023 2366 2.1×
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal Mantas Mazeika, Long Phan, Xu-Wang Yin vd.
Jailbreak ve red teaming 2024 1771 2.1×
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce, M. Hein
Adversarial örnekler ve sağlamlık 2020 2641 2×
Theoretically Principled Trade-off between Robustness and Accuracy Hongyang Zhang, Yaodong Yu, Jian-Tao Jiao vd.
Adversarial örnekler ve sağlamlık 2019 3263 1.9×
Is Feature Selection Secure against Training Data Poisoning? Huang Xiao, B. Biggio, Gavin Brown vd.
Zehirleme ve arka kapılar 2015 448 1.9×
Defeating Prompt Injections by Design Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan vd.
Savunmalar, guardrail ve filigran 2025 396 1.8×
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples Anish Athalye, Nicholas Carlini, D. Wagner
Adversarial örnekler ve sağlamlık 2018 3730 1.7×
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen, Elan Rosenfeld, J. Kolter
Adversarial örnekler ve sağlamlık 2019 2722 1.7×
Jailbreaking Black Box Large Language Models in Twenty Queries Patrick Chao, Alexander Robey, Edgar Dobriban vd.
Jailbreak ve red teaming 2023 1847 1.7×
Refusal in Language Models Is Mediated by a Single Direction Andy Arditi, O. Obeso, Aaquib Syed vd.
Jailbreak ve red teaming 2024 1253 1.7×
Inverting Gradients - How easy is it to break privacy in federated learning? Jonas Geiping, Hartmut Bauermeister, Hannah Dröge vd.
Gizlilik ve model çalma 2020 1896 1.5×
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations Hakan Inan, K. Upasani, Jianfeng Chi vd.
Savunmalar, guardrail ve filigran 2023 1506 1.5×
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks Kimin Lee, Kibok Lee, Honglak Lee vd.
Adversarial örnekler ve sağlamlık 2018 2989 1.4×
Natural Adversarial Examples Dan Hendrycks, Kevin Zhao, Steven Basart vd.
Adversarial örnekler ve sağlamlık 2019 2111 1.4×
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! Xiangyu Qi, Yi Zeng, Tinghao Xie vd.
Jailbreak ve red teaming 2023 1478 1.4×
Adversarial Machine Learning at Scale Alexey Kurakin, I. Goodfellow, Samy Bengio
Adversarial örnekler ve sağlamlık 2016 3470 1.3×
How To Backdoor Federated Learning Eugene Bagdasarian, Andreas Veit, Yiqing Hua vd.
Zehirleme ve arka kapılar 2018 2793 1.3×
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning Minghong Fang, Xiaoyu Cao, Jinyuan Jia vd.
Zehirleme ve arka kapılar 2019 1770 1.3×
Ensemble Adversarial Training: Attacks and Defenses Florian Tramèr, Alexey Kurakin, Nicolas Papernot vd.
Adversarial örnekler ve sağlamlık 2017 3168 1.2×
One Pixel Attack for Fooling Deep Neural Networks Jiawei Su, Danilo Vasconcellos Vargas, K. Sakurai
Adversarial örnekler ve sağlamlık 2017 2669 1.2×
Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras vd.
Adversarial örnekler ve sağlamlık 2019 2214 1.2×
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature E. Mitchell, Yoonho Lee, Alexander Khazatsky vd.
Savunmalar, guardrail ve filigran 2023 1327 1.2×
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents Pritam Dash, Tongyu Ge, Aditi Jain vd.
Prompt injection ve agent güvenliği 2026 40 1.2×
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Xin-Yun Chen, Chang Liu, Bo Li vd.
Zehirleme ve arka kapılar 2017 2446 1.1×
Fast is better than free: Revisiting adversarial training Eric Wong, L. Rice, J. Kolter
Adversarial örnekler ve sağlamlık 2020 1441 1.1×
RobustBench: a standardized adversarial robustness benchmark Francesco Croce, Maksym Andriushchenko, Vikash Sehwag vd.
Adversarial örnekler ve sağlamlık 2020 1002 1.1×
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale Yi Liu, Wei-Zhe Wang, Rui Feng vd.
Prompt injection ve agent güvenliği 2026 129 1.1×
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain Tianyu Gu, Brendan Dolan-Gavitt, Siddharth Garg
Zehirleme ve arka kapılar 2017 2516 1×
Stealing Machine Learning Models via Prediction APIs Florian Tramèr, Fan Zhang, A. Juels vd.
Gizlilik ve model çalma 2016 2273 1×
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey Naveed Akhtar, Ajmal Saeed Mian
Adversarial örnekler ve sağlamlık 2018 2134 1×
Poisoning Attacks against Support Vector Machines B. Biggio, B. Nelson, P. Laskov
Zehirleme ve arka kapılar 2012 1927 1×
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment Di Jin, Zhijing Jin, Joey Tianyi Zhou vd.
Adversarial örnekler ve sağlamlık 2019 1463 1×
Square Attack: a query-efficient black-box adversarial attack via random search Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion vd.
Adversarial örnekler ve sağlamlık 2019 1367 1×
Ignore Previous Prompt: Attack Techniques For Language Models Fábio Perez, I. Ribeiro
Prompt injection ve agent güvenliği 2022 1204 1×
A Watermark for Large Language Models John Kirchenbauer, Jonas Geiping, Yuxin Wen vd.
Savunmalar, guardrail ve filigran 2023 1138 1×
Extracting Training Data from Diffusion Models Nicholas Carlini, Jamie Hayes, Milad Nasr vd.
Gizlilik ve model çalma 2023 1105 1×
Data Poisoning Attacks Against Federated Learning Systems Vale Tolpegin, Stacey Truex, M. E. Gursoy vd.
Zehirleme ve arka kapılar 2020 1017 1×
Membership Inference Attacks on Machine Learning: A Survey Hongsheng Hu, Z. Salcic, Lichao Sun vd.
Gizlilik ve model çalma 2021 757 1×
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian vd.
Prompt injection ve agent güvenliği 2024 538 1×
Prompt Injection Attack to Tool Selection in LLM Agents Jia-Wen Shi, Zenghui Yuan, Guiyao Tie vd.
Prompt injection ve agent güvenliği 2025 200 1×
DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks Yupei Liu, Yu-Qi Jia, Jin-Yuan Jia vd.
Savunmalar, guardrail ve filigran 2025 197 1×
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks Ivan Evtimov, A. Zharmagambetov, Aaron Grattafiori vd.
Prompt injection ve agent güvenliği 2025 195 1×
Qwen3Guard Technical Report Hai-Quan Zhao, Chen-Han Yuan, Fei Huang vd.
Savunmalar, guardrail ve filigran 2025 166 1×
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections Milad Nasr, Nicholas Carlini, Chawin Sitawarin vd.
Jailbreak ve red teaming 2025 164 1×
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi vd.
Prompt injection ve agent güvenliği 2026 104 1×
Natural Backdoor Attacks on Speech Recognition Models Jinwen Xin, Xixiang Lyu, Jing Ma
Zehirleme ve arka kapılar 2026 24 1×
ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models Pin-Yu Chen, Huan Zhang, Yash Sharma vd.
Adversarial örnekler ve sağlamlık 2017 2308 0.9×
Robustness May Be at Odds with Accuracy Dimitris Tsipras, Shibani Santurkar, Logan Engstrom vd.
Adversarial örnekler ve sağlamlık 2018 2062 0.9×
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples Nicolas Papernot, P. McDaniel, I. Goodfellow
Adversarial örnekler ve sağlamlık 2016 1977 0.9×
Adversarial Examples: Attacks and Defenses for Deep Learning Xiaoyong Yuan, Pan He, Qile Zhu vd.
Adversarial örnekler ve sağlamlık 2017 1901 0.9×
Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning B. Biggio, F. Roli
Adversarial örnekler ve sağlamlık 2017 1853 0.9×
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods Dylan Slack, Sophie Hilgard, Emily Jia vd.
Adversarial örnekler ve sağlamlık 2019 1295 0.9×
Graph Structure Learning for Robust Graph Neural Networks Wei Jin, Yao Ma, Xiaorui Liu vd.
Adversarial örnekler ve sağlamlık 2020 996 0.9×
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models Xiaogeng Liu, Nan Xu, Muhao Chen vd.
Jailbreak ve red teaming 2023 972 0.9×
Prompt Injection attack against LLM-integrated Applications Yi Liu, Ge-Lei Deng, Yuekang Li vd.
Prompt injection ve agent güvenliği 2023 955 0.9×
Backdoor Learning: A Survey Yiming Li, Baoyuan Wu, Yong Jiang vd.
Zehirleme ve arka kapılar 2020 911 0.9×
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically Anay Mehrotra, M. Zampetakis, Paul Kassianik vd.
Jailbreak ve red teaming 2023 883 0.9×
Diffusion Models for Adversarial Purification Weili Nie, Brandon Guo, Yujia Huang vd.
Adversarial örnekler ve sağlamlık 2022 793 0.9×
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents Qiusi Zhan, Zhi-Xiang Liang, Zifan Ying vd.
Prompt injection ve agent güvenliği 2024 790 0.9×
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs Yi Zeng, Hong-Yi Lin, Jing-Wen Zhang vd.
Jailbreak ve red teaming 2024 772 0.9×
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models Patrick Chao, Edoardo Debenedetti, Alexander Robey vd.
Jailbreak ve red teaming 2024 742 0.9×
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases Zhaorun Chen, Zhen Xiang, Chao-Wei Xiao vd.
Prompt injection ve agent güvenliği 2024 593 0.9×
Anti-Backdoor Learning: Training Clean Models on Poisoned Data Yi-Ge Li, Xixiang Lyu, Nodens Koren vd.
Zehirleme ve arka kapılar 2021 511 0.9×
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents Hanrong Zhang, Jingyuan Huang, Kai Mei vd.
Prompt injection ve agent güvenliği 2024 482 0.9×
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Mrinank Sharma, Meg Tong, Jesse Mu vd.
Savunmalar, guardrail ve filigran 2025 211 0.9×
Progent: Securing AI Agents with Privilege Control Tian-Neng Shi, Jing-Xuan He, Zhun Wang vd.
Savunmalar, guardrail ve filigran 2025 180 0.9×
Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems Yubin Qu, Yi Liu, Tong-Cheng Geng vd.
Prompt injection ve agent güvenliği 2026 49 0.9×
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents Sidharth Pulipaka, Stanislau Hlebik, Leonidas Raghav vd.
Prompt injection ve agent güvenliği 2026 37 0.9×
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods Nicholas Carlini, D. Wagner
Adversarial örnekler ve sağlamlık 2017 2067 0.8×
Exploiting Unintended Feature Leakage in Collaborative Learning Luca Melis, Cong-Zheng Song, Emiliano De Cristofaro vd.
Gizlilik ve model çalma 2018 1881 0.8×
Countering Adversarial Images using Input Transformations Chuan Guo, Mayank Rana, M. Cissé vd.
Adversarial örnekler ve sağlamlık 2018 1687 0.8×
Adversarial Training for Free! Ali Shafahi, Mahyar Najibi, Amin Ghiasi vd.
Adversarial örnekler ve sağlamlık 2019 1510 0.8×
Universal Adversarial Triggers for Attacking and Analyzing NLP Eric Wallace, Shi Feng, Nikhil Kandpal vd.
Adversarial örnekler ve sağlamlık 2019 1173 0.8×
On Adaptive Attacks to Adversarial Example Defenses Florian Tramèr, Nicholas Carlini, Wieland Brendel vd.
Adversarial örnekler ve sağlamlık 2020 1059 0.8×
Overfitting in adversarially robust deep learning L. Rice, Eric Wong, J. Kolter
Adversarial örnekler ve sağlamlık 2020 992 0.8×
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned Deep Ganguli, Liane Lovitt, John Kernion vd.
Jailbreak ve red teaming 2022 920 0.8×
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning Hongyi Wang, K. Sreenivasan, Shashank Rajput vd.
Zehirleme ve arka kapılar 2020 874 0.8×
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models Xinyue Shen, Zeyuan Chen, M. Backes vd.
Jailbreak ve red teaming 2023 797 0.8×
Invisible Backdoor Attack with Sample-Specific Triggers Yue-Zun Li, Yiming Li, Baoyuan Wu vd.
Zehirleme ve arka kapılar 2020 731 0.8×
Recent Advances in Adversarial Training for Adversarial Robustness Tao Bai, Jinqi Luo, Jun Zhao vd.
Adversarial örnekler ve sağlamlık 2021 675 0.8×
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions Eric Wallace, Kai Xiao, R. Leike vd.
Savunmalar, guardrail ve filigran 2024 632 0.8×
Enhancing the Transferability of Adversarial Attacks through Variance Tuning Xiaosen Wang, Kun He
Adversarial örnekler ve sağlamlık 2021 629 0.8×
Safety Alignment Should Be Made More Than Just a Few Tokens Deep Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu vd.
Jailbreak ve red teaming 2024 565 0.8×
On the Convergence and Robustness of Adversarial Training Yisen Wang, Xingjun Ma, James Bailey vd.
Adversarial örnekler ve sağlamlık 2021 396 0.8×
Deliberative Alignment: Reasoning Enables Safer Language Models Melody Y. Guan, Manas R. Joglekar, Eric Wallace vd.
Savunmalar, guardrail ve filigran 2024 329 0.8×
DeepSign: Deep learning for automatic malware signature generation and classification Omid David, N. Netanyahu
Güvenlik için yapay zeka 2015 224 0.8×
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents Qiusi Zhan, Richard Fang, H. Panchal vd.
Prompt injection ve agent güvenliği 2025 183 0.8×
LlamaFirewall: An open source guardrail system for building secure AI agents Sahana Chennabasappa, Cyrus Nikolaidis, D. Song vd.
Savunmalar, guardrail ve filigran 2025 156 0.8×
PromptArmor: Simple yet Effective Prompt Injection Defenses Tian-Neng Shi, Kai-Jie Zhu, Zhun Wang vd.
Savunmalar, guardrail ve filigran 2025 140 0.8×
MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills Wenbo Guo, Wei Zeng, Cheng-Wei Liu vd.
Prompt injection ve agent güvenliği 2026 28 0.8×
Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees Yedidel Louck
Savunmalar, guardrail ve filigran 2026 24 0.8×
Stealing Reasoning Traces from Proprietary LLM APIs Alexander Panfilov, David Schmotz, I. Shumailov vd.
Gizlilik ve model çalma 2026 16 0.8×
JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models Jian-Yi Hu, Hang Zhang, Yi Liu vd.
Adversarial örnekler ve sağlamlık 2026 15 0.8×
Delving into Transferable Adversarial Examples and Black-box Attacks Yan-Pei Liu, Xin-Yun Chen, Chang Liu vd.
Adversarial örnekler ve sağlamlık 2016 2049 0.7×
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks Weilin Xu, David Evans, Yan-Jun Qi
Adversarial örnekler ve sağlamlık 2017 1820 0.7×
Adversarial Examples for Evaluating Reading Comprehension Systems Robin Jia, Percy Liang
Adversarial örnekler ve sağlamlık 2017 1784 0.7×
Provable defenses against adversarial examples via the convex outer adversarial polytope Eric Wong, J. Kolter
Adversarial örnekler ve sağlamlık 2017 1664 0.7×
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models Wieland Brendel, Jonas Rauber, M. Bethge
Adversarial örnekler ve sağlamlık 2017 1605 0.7×
Improving Transferability of Adversarial Examples With Input Diversity Cihang Xie, Zhishuai Zhang, Yuyin Zhou vd.
Adversarial örnekler ve sağlamlık 2018 1546 0.7×
Analyzing Federated Learning through an Adversarial Lens A. Bhagoji, Supriyo Chakraborty, Prateek Mittal vd.
Zehirleme ve arka kapılar 2018 1421 0.7×
STRIP: a defence against trojan attacks on deep neural networks Yan-Song Gao, Chang Xu, De-Rui Wang vd.
Zehirleme ve arka kapılar 2019 1165 0.7×
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Dan Hendrycks, Mantas Mazeika, Saurav Kadavath vd.
Adversarial örnekler ve sağlamlık 2019 1116 0.7×
On Evaluating Adversarial Robustness Nicholas Carlini, Anish Athalye, Nicolas Papernot vd.
Adversarial örnekler ve sağlamlık 2019 1095 0.7×
BERT-ATTACK: Adversarial Attack against BERT Using BERT Linyang Li, Ruotian Ma, Qipeng Guo vd.
Adversarial örnekler ve sağlamlık 2020 945 0.7×
Baseline Defenses for Adversarial Attacks Against Aligned Language Models Neel Jain, Avi Schwarzschild, Yuxin Wen vd.
Savunmalar, guardrail ve filigran 2023 830 0.7×
Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study Yi Liu, Ge-Lei Deng, Zheng-Zi Xu vd.
Jailbreak ve red teaming 2023 743 0.7×
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models Boxin Wang, Weixin Chen, Hengzhi Pei vd.
Jailbreak ve red teaming 2023 739 0.7×
From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy Maanak Gupta, Charankumar Akiri, Kshitiz Aryal vd.
Güvenlik için yapay zeka 2023 709 0.7×
Label-Only Membership Inference Attacks Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini vd.
Gizlilik ve model çalma 2020 669 0.7×
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Evan Hubinger, Carson Denison, Jesse Mu vd.
Zehirleme ve arka kapılar 2024 644 0.7×
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks Yi-Ge Li, Xixiang Lyu, Nodens Koren vd.
Zehirleme ve arka kapılar 2021 623 0.7×
Privacy and Robustness in Federated Learning: Attacks and Defenses L. Lyu, Han Yu, Xingjun Ma vd.
Zehirleme ve arka kapılar 2020 590 0.7×
Security and Privacy Challenges of Large Language Models: A Survey B. Das, M. Amini, Yanzhao Wu
Gizlilik ve model çalma 2024 581 0.7×
Enhanced Membership Inference Attacks against Machine Learning Models Jiayuan Ye, Aadyaa Maddi, S. K. Murakonda vd.
Gizlilik ve model çalma 2021 400 0.7×
Improving Robustness using Generated Data Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles vd.
Adversarial örnekler ve sağlamlık 2021 395 0.7×
Are Transformers More Robust Than CNNs? Yutong Bai, Jie-Ru Mei, A. Yuille vd.
Adversarial örnekler ve sağlamlık 2021 367 0.7×
Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges Nuria Rodríguez Barroso, Daniel Jiménez-López, M. V. Luzón vd.
Zehirleme ve arka kapılar 2022 330 0.7×
Memory Injection Attacks on LLM Agents via Query-Only Interaction Shen Dong, Shao-Chen Xu, Peng-Fei He vd.
Prompt injection ve agent güvenliği 2025 166 0.7×
Red-Teaming LLM Multi-Agent Systems via Communication Attacks Peng-Fei He, Yu-Ping Lin, Shen Dong vd.
Prompt injection ve agent güvenliği 2025 157 0.7×
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents Salman Rahman, Liwei Jiang, James Shiffer vd.
Jailbreak ve red teaming 2025 146 0.7×
TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems Shaina Raza, Ranjan Sapkota, Manoj Karkee vd.
Prompt injection ve agent güvenliği 2025 130 0.7×
From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows M. Ferrag, Norbert Tihanyi, Djallel Hamouda vd.
Prompt injection ve agent güvenliği 2025 127 0.7×
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents Thomas M. Kuntz, Agatha Duzan, Hao-Chen Zhao vd.
Prompt injection ve agent güvenliği 2025 126 0.7×
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback Yutao Mou, Zhangchi Xue, Lijun Li vd.
Savunmalar, guardrail ve filigran 2026 89 0.7×
Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions Tian-Tong Wu, Wei Yang Bryan Lim
Prompt injection ve agent güvenliği 2026 14 0.7×
DeepXplore: Automated Whitebox Testing of Deep Learning Systems Ke-Xin Pei, Yinzhi Cao, Junfeng Yang vd.
Adversarial örnekler ve sağlamlık 2017 1592 0.6×
Black-box Adversarial Attacks with Limited Queries and Information Andrew Ilyas, Logan Engstrom, Anish Athalye vd.
Adversarial örnekler ve sağlamlık 2018 1458 0.6×
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks Kang Liu, Brendan Dolan-Gavitt, Siddharth Garg
Zehirleme ve arka kapılar 2018 1454 0.6×
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks Ali Shafahi, W. R. Huang, Mahyar Najibi vd.
Zehirleme ve arka kapılar 2018 1344 0.6×
Adversarial Attacks on Neural Networks for Graph Data Daniel Zügner, Amir Akbarnejad, Stephan Günnemann
Adversarial örnekler ve sağlamlık 2018 1344 0.6×
Mitigating adversarial effects through randomization Cihang Xie, Jian-Yu Wang, Zhishuai Zhang vd.
Adversarial örnekler ve sağlamlık 2017 1253 0.6×
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text Nicholas Carlini, D. Wagner
Adversarial örnekler ve sağlamlık 2018 1228 0.6×
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks Yin-Peng Dong, Tianyu Pang, Hang Su vd.
Adversarial örnekler ve sağlamlık 2019 1179 0.6×
Spectral Signatures in Backdoor Attacks Brandon Tran, Jerry Li, A. Ma̧dry
Zehirleme ve arka kapılar 2018 1092 0.6×
Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks Jiadong Lin, Chuan-Biao Song, Kun He vd.
Adversarial örnekler ve sağlamlık 2019 854 0.6×
Hidden Trigger Backdoor Attacks Aniruddha Saha, Akshayvarun Subramanya, H. Pirsiavash
Zehirleme ve arka kapılar 2019 815 0.6×
Can You Really Backdoor Federated Learning? Ziteng Sun, Peter Kairouz, A. Suresh vd.
Zehirleme ve arka kapılar 2019 784 0.6×
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts Jiahao Yu, Xingwei Lin, Zheng Yu vd.
Jailbreak ve red teaming 2023 708 0.6×
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense Kalpesh Krishna, Yixiao Song, Marzena Karpinska vd.
Savunmalar, guardrail ve filigran 2023 697 0.6×
Can AI-Generated Text be Reliably Detected? Vinu Sankar Sadasivan, Aounon Kumar, S. Balasubramanian vd.
Savunmalar, guardrail ve filigran 2023 688 0.6×
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks Yunfei Liu, Xingjun Ma, James Bailey vd.
Zehirleme ve arka kapılar 2020 649 0.6×
Scalable Extraction of Training Data from (Production) Language Models Milad Nasr, Nicholas Carlini, J. Hayase vd.
Gizlilik ve model çalma 2023 637 0.6×
Input-Aware Dynamic Backdoor Attack A. Nguyen, A. Tran
Zehirleme ve arka kapılar 2020 618 0.6×
StruQ: Defending Against Prompt Injection with Structured Queries Si-Zhe Chen, Julien Piet, Chawin Sitawarin vd.
Savunmalar, guardrail ve filigran 2024 533 0.6×
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack M. Russinovich, Ahmed Salem, Ronen Eldan
Jailbreak ve red teaming 2024 491 0.6×
Vision Transformers are Robust Learners Sayak Paul, Pin-Yu Chen
Adversarial örnekler ve sağlamlık 2021 407 0.6×
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger Fanchao Qi, Mukai Li, Yangyi Chen vd.
Zehirleme ve arka kapılar 2021 384 0.6×
Feature Importance-aware Transferable Adversarial Attacks Zhibo Wang, Hengchang Guo, Zhifei Zhang vd.
Adversarial örnekler ve sağlamlık 2021 359 0.6×
Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning Virat Shejwalkar, Amir Houmansadr, Peter Kairouz vd.
Zehirleme ve arka kapılar 2021 350 0.6×
Advances in adversarial attacks and defenses in computer vision: A survey Naveed Akhtar, Ajmal Saeed Mian, Navid Kardan vd.
Adversarial örnekler ve sağlamlık 2021 350 0.6×
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models Boxin Wang, Che-Jian Xu, Shuo-Hang Wang vd.
Adversarial örnekler ve sağlamlık 2021 329 0.6×
SecAlign: Defending Against Prompt Injection with Preference Optimization Si-Zhe Chen, Arman Zharmagambetov, Saeed Mahloujifar vd.
Savunmalar, guardrail ve filigran 2024 291 0.6×
Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar vd.
Savunmalar, guardrail ve filigran 2025 183 0.6×
Unveiling Privacy Risks in LLM Agent Memory Bo Wang, Weiyi He, Peng-Fei He vd.
Prompt injection ve agent güvenliği 2025 147 0.6×
A Survey on Trustworthy LLM Agents: Threats and Countermeasures Miao Yu, Fanci Meng, Xinyun Zhou vd.
Prompt injection ve agent güvenliği 2025 144 0.6×
Design Patterns for Securing LLM Agents against Prompt Injections Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu vd.
Savunmalar, guardrail ve filigran 2025 109 0.6×
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples Alexandra Souly, Javier Rando, Ed Chapman vd.
Zehirleme ve arka kapılar 2025 101 0.6×
MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers Zhi-Qiang Wang, Yi-Chao Gao, Yan-Ting Wang vd.
Prompt injection ve agent güvenliği 2025 93 0.6×
MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval S. Srivastava, Hao-Yu He
Prompt injection ve agent güvenliği 2025 82 0.6×
AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments? Hao Li, Ruoyao Wen, Shang-Hao Shi vd.
Prompt injection ve agent güvenliği 2026 69 0.6×
Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework Zimo Ji, Dao-Yuan Wu, Wenyuan Jiang vd.
Savunmalar, guardrail ve filigran 2026 67 0.6×
AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations Yu He, Haozhe Zhu, Yi-Ming Li vd.
Savunmalar, guardrail ve filigran 2026 57 0.6×
BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning Guiyao Tie, Jia-Wen Shi, Pan Zhou vd.
Zehirleme ve arka kapılar 2026 30 0.6×
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection Shi-Hao Weng, Yang Feng, Jinrui Zhang vd.
Savunmalar, guardrail ve filigran 2026 25 0.6×
Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents Pei-Ran Wang, Ying Li, Yuan Tian
Savunmalar, guardrail ve filigran 2026 21 0.6×
MagNet: A Two-Pronged Defense against Adversarial Examples Dongyu Meng, Hao Chen
Adversarial örnekler ve sağlamlık 2017 1354 0.5×
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models Pouya Samangouei, Maya Kabkab, R. Chellappa
Adversarial örnekler ve sağlamlık 2018 1296 0.5×
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models A. Salem, Yang Zhang, Mathias Humbert vd.
Gizlilik ve model çalma 2018 1235 0.5×
Interpretation of Neural Networks is Fragile Amirata Ghorbani, Abubakar Abid, James Y. Zou
Adversarial örnekler ve sağlamlık 2017 1140 0.5×
Certified Robustness to Adversarial Examples with Differential Privacy Mathias Lécuyer, Vaggelis Atlidakis, Roxana Geambasu vd.
Adversarial örnekler ve sağlamlık 2018 1088 0.5×
Generating Adversarial Examples with Adversarial Networks Chaowei Xiao, Bo Li, Jun-Yan Zhu vd.
Adversarial örnekler ve sağlamlık 2018 1078 0.5×
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser Fangzhou Liao, Ming Liang, Yin-Peng Dong vd.
Adversarial örnekler ve sağlamlık 2017 1067 0.5×
Generating Natural Language Adversarial Examples M. Alzantot, Yash Sharma, Ahmed Elgohary vd.
Adversarial örnekler ve sağlamlık 2018 1065 0.5×
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering Bryant Chen, Wilka Carvalho, Nathalie Baracaldo vd.
Zehirleme ve arka kapılar 2018 1049 0.5×
Feature Denoising for Improving Adversarial Robustness Cihang Xie, Yuxin Wu, L. van der Maaten vd.
Adversarial örnekler ve sağlamlık 2018 1035 0.5×
Certified Defenses against Adversarial Examples Aditi Raghunathan, Jacob Steinhardt, Percy Liang
Adversarial örnekler ve sağlamlık 2018 1026 0.5×
Efficient Neural Network Robustness Certification with General Activation Functions Huan Zhang, T. Weng, Pin-Yu Chen vd.
Adversarial örnekler ve sağlamlık 2018 988 0.5×
HopSkipJumpAttack: A Query-Efficient Decision-Based Attack Jianbo Chen, Michael I. Jordan, Martin J. Wainwright
Adversarial örnekler ve sağlamlık 2019 896 0.5×
Using Pre-Training Can Improve Model Robustness and Uncertainty Dan Hendrycks, Kimin Lee, Mantas Mazeika
Adversarial örnekler ve sağlamlık 2019 884 0.5×
Unlabeled Data Improves Adversarial Robustness Y. Carmon, Aditi Raghunathan, Ludwig Schmidt vd.
Adversarial örnekler ve sağlamlık 2019 826 0.5×
Adversarial Attacks and Defenses in Images, Graphs and Text: A Review Han Xu, Yao Ma, Haochen Liu vd.
Adversarial örnekler ve sağlamlık 2019 776 0.5×
BAE: BERT-based Adversarial Examples for Text Classification Siddhant Garg, Goutham Ramakrishnan
Adversarial örnekler ve sağlamlık 2020 690 0.5×
Weight Poisoning Attacks on Pretrained Models Keita Kurita, Paul Michel, Graham Neubig
Zehirleme ve arka kapılar 2020 652 0.5×
Adversarial Examples Improve Image Recognition Cihang Xie, Mingxing Tan, Boqing Gong vd.
Adversarial örnekler ve sağlamlık 2019 640 0.5×
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Alexander Robey, Eric Wong, Hamed Hassani vd.
Savunmalar, guardrail ve filigran 2023 591 0.5×
Formalizing and Benchmarking Prompt Injection Attacks and Defenses Yupei Liu, Yu-Qi Jia, Runpeng Geng vd.
Prompt injection ve agent güvenliği 2023 583 0.5×
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation Yangsibo Huang, Samyak Gupta, Mengzhou Xia vd.
Jailbreak ve red teaming 2023 582 0.5×
Toxicity in ChatGPT: Analyzing Persona-assigned Language Models A. Deshpande, Vishvak Murahari, Tanmay Rajpurohit vd.
Jailbreak ve red teaming 2023 561 0.5×
Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations Zeming Wei, Yi-Fei Wang, Ang Li vd.
Jailbreak ve red teaming 2023 545 0.5×
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher Youliang Yuan, Wenxiang Jiao, Wenxuan Wang vd.
Jailbreak ve red teaming 2023 537 0.5×
FigStep: Jailbreaking Large Vision-language Models via Typographic Visual Prompts Yichen Gong, De-Long Ran, Jinyuan Liu vd.
Jailbreak ve red teaming 2023 516 0.5×
Do Adversarially Robust ImageNet Models Transfer Better? Hadi Salman, Andrew Ilyas, Logan Engstrom vd.
Adversarial örnekler ve sağlamlık 2020 515 0.5×
Multi-step Jailbreaking Privacy Attacks on ChatGPT Haoran Li, Dadi Guo, Wei Fan vd.
Gizlilik ve model çalma 2023 509 0.5×
Amnesiac Machine Learning Laura Graves, Vineel Nagisetty, Vijay Ganesh
Gizlilik ve model çalma 2020 504 0.5×
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks Fanchao Qi, Yangyi Chen, Mukai Li vd.
Zehirleme ve arka kapılar 2020 467 0.5×
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum, Dimitris Tsipras, Chulin Xie vd.
Zehirleme ve arka kapılar 2020 443 0.5×
FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients Zaixi Zhang, Xiaoyu Cao, Jin-Yuan Jia vd.
Zehirleme ve arka kapılar 2022 441 0.5×
Benchmarking and Defending against Indirect Prompt Injection Attacks on Large Language Models Jing-Wei Yi, Yueqi Xie, Bin Zhu vd.
Prompt injection ve agent güvenliği 2023 418 0.5×
Improving Alignment and Robustness with Circuit Breakers Andy Zou, Long Phan, Justin Wang vd.
Savunmalar, guardrail ve filigran 2024 375 0.5×
Gradient-based Adversarial Attacks against Text Transformers Chuan Guo, Alexandre Sablayrolles, Hervé Jégou vd.
Adversarial örnekler ve sağlamlık 2021 350 0.5×
PPFL: privacy-preserving federated learning with trusted execution environments Fan Mo, H. Haddadi, Kleomenis Katevas vd.
Gizlilik ve model çalma 2021 339 0.5×
Jailbreak Attacks and Defenses Against Large Language Models: A Survey Si-Bo Yi, Yule Liu, Zhen Sun vd.
Jailbreak ve red teaming 2024 317 0.5×
Backdoor Defense via Decoupling the Training Process Kunzhe Huang, Yiming Li, Baoyuan Wu vd.
Zehirleme ve arka kapılar 2022 285 0.5×
Adversarial Unlearning of Backdoors via Implicit Hypergradient Yi Zeng, Si Chen, Won Park vd.
Zehirleme ve arka kapılar 2021 279 0.5×
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer Fanchao Qi, Yangyi Chen, Xurui Zhang vd.
Zehirleme ve arka kapılar 2021 277 0.5×
DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection P. Rieger, T. Nguyen, Markus Miettinen vd.
Zehirleme ve arka kapılar 2022 267 0.5×
Natural Attack for Pre-trained Models of Code Zhou Yang, Jie-Ke Shi, Jun-Da He vd.
Adversarial örnekler ve sağlamlık 2022 248 0.5×
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 Kai-Qing Zhou, Cheng-Zhi Liu, Xuandong Zhao vd.
Jailbreak ve red teaming 2025 116 0.5×
Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents Juhee Kim, Woohyuk Choi, Byoungyoung Lee
Savunmalar, guardrail ve filigran 2025 104 0.5×
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents C. D. de Witt
Prompt injection ve agent güvenliği 2025 102 0.5×
DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents Hao Li, Xiaogeng Liu, Hung-Chun Chiu vd.
Savunmalar, guardrail ve filigran 2025 90 0.5×
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents Heng-Yu An, Jing-Huai Zhang, Tianyu Du vd.
Savunmalar, guardrail ve filigran 2025 82 0.5×
A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory Qian-Shan Wei, Teng-Chao Yang, Yaochen Wang vd.
Savunmalar, guardrail ve filigran 2025 78 0.5×
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild Yi Liu, Zhi-Hao Chen, Yan-Jun Zhang vd.
Prompt injection ve agent güvenliği 2026 58 0.5×
Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections Xiang-Lin Yang, Yu-Fei He, Shuo Ji vd.
Prompt injection ve agent güvenliği 2026 49 0.5×
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle Zehao Lin, Xi-Xuan Hao, Ren-Yu Fu vd.
Prompt injection ve agent güvenliği 2026 26 0.5×
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems Yun-Hao Feng, Yi-Fan Ding, Ying-Shui Tan vd.
Zehirleme ve arka kapılar 2026 26 0.5×
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms Qi Li, Bo Yin, Weiqi Huang vd.
Prompt injection ve agent güvenliği 2026 21 0.5×
What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents Xiaoqian Weng
Savunmalar, guardrail ve filigran 2026 18 0.5×
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems Yichen Xie, Jia-Wei Du, Yu Cheng vd.
Prompt injection ve agent güvenliği 2026 16 0.5×
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents Shi-Yang Chen
Prompt injection ve agent güvenliği 2026 14 0.5×
Context-to-Execution Integrity for LLM Agents Igor Santos-Grueiro
Prompt injection ve agent güvenliği 2026 12 0.5×
GPT-Red: Automated Red Teaming via Self-Play at Scale Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal vd.
Jailbreak ve red teaming 2026 10 0.5×
Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory Jing-Heng Xu, Yi-Yong Xiao, Wanru Shao vd.
Savunmalar, guardrail ve filigran 2026 9 0.5×