{"total":166,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672,"area":"safety"},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486,"area":"safety"},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469,"area":"safety"},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244,"area":"safety"},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222,"area":"safety"},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158,"area":"safety"},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145,"area":"safety"},{"id":"2504.11358","title":"DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks","created":"2025-04-15","cited_by_count":143,"area":"safety"},{"id":"2306.01953","title":"Invisible Image Watermarks Are Provably Removable Using Generative AI","created":"2023-06-02","cited_by_count":134,"area":"safety"},{"id":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134,"area":"safety"},{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129,"area":"safety"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89,"area":"safety"},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79,"area":"safety"},{"id":"2305.03807","title":"Evading Watermark based Detection of AI-Generated Content","created":"2023-05-05","cited_by_count":78,"area":"safety"},{"id":"2104.09667","title":"Manipulating SGD with Data Ordering Attacks","created":"2021-04-19","cited_by_count":74,"area":"safety"},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2301.11578","title":"Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers","created":"2023-01-27","cited_by_count":67,"area":"safety"},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62,"area":"safety"},{"id":"2412.00473","title":"Jailbreak Large Vision-Language Models Through Multi-Modal Linkage","created":"2024-11-30","cited_by_count":62,"area":"safety"},{"id":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60,"area":"safety"},{"id":"2211.02408","title":"Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis","created":"2022-11-04","cited_by_count":59,"area":"safety"},{"id":"2109.08266","title":"Hard to Forget: Poisoning Attacks on Certified Machine Unlearning","created":"2021-09-17","cited_by_count":52,"area":"safety"},{"id":"2102.10496","title":"Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits","created":"2021-02-21","cited_by_count":49,"area":"safety"},{"id":"2601.11516","title":"Building Production-Ready Probes For Gemini","created":"2026-01-16","cited_by_count":47,"area":"safety"},{"id":"2106.14851","title":"Data Poisoning Won't Save You From Facial Recognition","created":"2021-06-28","cited_by_count":45,"area":"safety"},{"id":"2405.01229","title":"Boosting Jailbreak Attack with Momentum","created":"2024-05-02","cited_by_count":40,"area":"safety"},{"id":"2112.07668","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","created":"2021-12-14","cited_by_count":37,"area":"safety"},{"id":"2111.07608","title":"Property Inference Attacks Against GANs","created":"2021-11-15","cited_by_count":33,"area":"safety"},{"id":"2303.15127","title":"Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks","created":"2023-03-27","cited_by_count":30,"area":"safety"},{"id":"2202.13585","title":"Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten","created":"2022-02-28","cited_by_count":25,"area":"safety"},{"id":"2204.09092","title":"Indiscriminate Data Poisoning Attacks on Neural Networks","created":"2022-04-19","cited_by_count":25,"area":"safety"},{"id":"2112.02797","title":"ML Attack Models: Adversarial Attacks and Data Poisoning Attacks","created":"2021-12-06","cited_by_count":24,"area":"safety"},{"id":"2303.03592","title":"Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks","created":"2023-03-07","cited_by_count":23,"area":"safety"},{"id":"2306.07754","title":"Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis","created":"2023-06-13","cited_by_count":23,"area":"safety"},{"id":"2208.10224","title":"Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks","created":"2022-08-14","cited_by_count":21,"area":"safety"},{"id":"2206.12381","title":"Defending Backdoor Attacks on Vision Transformer via Patch Processing","created":"2022-06-24","cited_by_count":20,"area":"safety"},{"id":"2405.20778","title":"Improved Generation of Adversarial Examples Against Safety-aligned LLMs","created":"2024-05-28","cited_by_count":18,"area":"safety"},{"id":"2407.07485","title":"Zero-Shot Class Unlearning in CLIP with Synthetic Samples","created":"2024-07-10","cited_by_count":17,"area":"safety"},{"id":"2410.09591","title":"Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy","created":"2024-10-12","cited_by_count":17,"area":"safety"},{"id":"2505.21277","title":"Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space","created":"2025-05-27","cited_by_count":17,"area":"safety"},{"id":"2405.14189","title":"Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization","created":"2024-05-23","cited_by_count":16,"area":"safety"},{"id":"2410.03489","title":"Gradient-based Jailbreak Images for Multimodal Fusion Models","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14,"area":"safety"},{"id":"2207.12405","title":"Versatile Weight Attack via Flipping Limited Bits","created":"2022-07-25","cited_by_count":13,"area":"safety"},{"id":"2404.17867","title":"Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics","created":"2024-04-27","cited_by_count":13,"area":"safety"},{"id":"2405.16978","title":"OSLO: One-Shot Label-Only Membership Inference Attacks","created":"2024-05-27","cited_by_count":13,"area":"safety"},{"id":"2303.14325","title":"Backdoor Attacks with Input-unique Triggers in NLP","created":"2023-03-25","cited_by_count":12,"area":"safety"},{"id":"2304.11285","title":"Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks","created":"2023-04-22","cited_by_count":12,"area":"safety"},{"id":"2301.01044","title":"Analysis of Label-Flip Poisoning Attack on Machine Learning Based Malware Detector","created":"2023-01-03","cited_by_count":11,"area":"safety"},{"id":"2406.07778","title":"A Study of Backdoors in Instruction Fine-tuned Language Models","created":"2024-06-12","cited_by_count":11,"area":"safety"},{"id":"2503.08704","title":"Life-Cycle Routing Vulnerabilities of LLM Router","created":"2025-03-09","cited_by_count":11,"area":"safety"},{"id":"2211.07915","title":"Backdoor Attacks on Time Series: A Generative Approach","created":"2022-11-15","cited_by_count":10,"area":"safety"},{"id":"2309.04777","title":"Towards Robust Model Watermark via Reducing Parametric Vulnerability","created":"2023-09-09","cited_by_count":10,"area":"safety"},{"id":"2103.12399","title":"The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?","created":"2021-03-23","cited_by_count":9,"area":"safety"},{"id":"2106.00660","title":"Markpainting: Adversarial Machine Learning meets Inpainting","created":"2021-06-01","cited_by_count":9,"area":"safety"},{"id":"2502.09638","title":"Jailbreaking to Jailbreak","created":"2025-02-09","cited_by_count":9,"area":"safety"},{"id":"2101.06898","title":"What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space","created":"2021-01-18","cited_by_count":8,"area":"safety"},{"id":"2205.06986","title":"Evaluating Membership Inference Through Adversarial Robustness","created":"2022-05-14","cited_by_count":8,"area":"safety"},{"id":"2401.01085","title":"Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control","created":"2024-01-02","cited_by_count":8,"area":"safety"},{"id":"2402.12626","title":"Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors","created":"2024-02-20","cited_by_count":8,"area":"safety"},{"id":"2501.16497","title":"Smoothed Embeddings for Robust Language Models","created":"2025-01-27","cited_by_count":8,"area":"safety"},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2505.21074","title":"Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling","created":"2025-05-27","cited_by_count":8,"area":"safety"},{"id":"2308.13768","title":"Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content","created":"2023-08-26","cited_by_count":7,"area":"safety"},{"id":"2505.15753","title":"Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval","created":"2025-05-21","cited_by_count":7,"area":"safety"},{"id":"2510.16794","title":"Black-box Optimization of LLM Outputs by Asking for Directions","created":"2025-10-19","cited_by_count":7,"area":"safety"},{"id":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","cited_by_count":7,"area":"safety"},{"id":"2111.01363","title":"Knowledge Cross-Distillation for Membership Privacy","created":"2021-11-02","cited_by_count":6,"area":"safety"},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2602.08563","title":"Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs","created":"2026-02-09","cited_by_count":6,"area":"safety"},{"id":"2602.12418","title":"Sparse Autoencoders are Capable LLM Jailbreak Mitigators","created":"2026-02-12","cited_by_count":6,"area":"safety"},{"id":"2209.01721","title":"An Adaptive Black-box Defense against Trojan Attacks (TrojDef)","created":"2022-09-05","cited_by_count":5,"area":"safety"},{"id":"2312.14440","title":"Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks","created":"2023-12-22","cited_by_count":5,"area":"safety"},{"id":"2402.05723","title":"In-Context Learning Can Re-learn Forbidden Tasks","created":"2024-02-08","cited_by_count":5,"area":"safety"},{"id":"2502.16423","title":"Unified Prompt Attack Against Text-to-Image Generation Models","created":"2025-02-23","cited_by_count":5,"area":"safety"},{"id":"2212.03334","title":"Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning","created":"2022-12-06","cited_by_count":4,"area":"safety"},{"id":"2301.03118","title":"Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons","created":"2023-01-08","cited_by_count":4,"area":"safety"},{"id":"2402.14977","title":"Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models","created":"2024-02-22","cited_by_count":4,"area":"safety"},{"id":"2404.02067","title":"Red-Teaming Segment Anything Model","created":"2024-04-02","cited_by_count":4,"area":"safety"},{"id":"2407.00075","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference","created":"2024-06-21","cited_by_count":4,"area":"safety"},{"id":"2407.12069","title":"Unlearning Personal Data from a Single Image","created":"2024-07-16","cited_by_count":4,"area":"safety"},{"id":"2410.04234","title":"Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks","created":"2024-10-05","cited_by_count":4,"area":"safety"},{"id":"2410.04682","title":"On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning","created":"2024-10-07","cited_by_count":4,"area":"safety"},{"id":"2503.01926","title":"Unnatural Languages Are Not Bugs but Features for LLMs","created":"2025-03-02","cited_by_count":4,"area":"safety"},{"id":"2505.09820","title":"Adversarial Attack on Large Language Models using Exponentiated Gradient Descent","created":"2025-05-14","cited_by_count":4,"area":"safety"},{"id":"2508.03365","title":"When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs","created":"2025-08-05","cited_by_count":4,"area":"safety"},{"id":"2510.26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","created":"2025-10-30","cited_by_count":4,"area":"safety"},{"id":"2602.16944","title":"Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programming","created":"2026-02-18","cited_by_count":4,"area":"safety"},{"id":"2101.00157","title":"Active Learning Under Malicious Mislabeling and Poisoning Attacks","created":"2021-01-01","cited_by_count":3,"area":"safety"},{"id":"2304.14483","title":"Adversary Aware Continual Learning","created":"2023-04-27","cited_by_count":3,"area":"safety"},{"id":"2312.11500","title":"A Red Teaming Framework for Securing AI in Maritime Autonomous Systems","created":"2023-12-08","cited_by_count":3,"area":"safety"}],"next_cursor":"100"}