{"total":92,"rows":[{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375,"area":"safety"},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333,"area":"safety"},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215,"area":"safety"},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157,"area":"safety"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110,"area":"safety"},{"id":"2312.17673","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","created":"2023-12-29","cited_by_count":106,"area":"safety"},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"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":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76,"area":"safety"},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76,"area":"safety"},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"area":"safety"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2308.10819","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","created":"2023-08-17","cited_by_count":59,"area":"safety"},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"area":"safety"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55,"area":"safety"},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54,"area":"safety"},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39,"area":"safety"},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38,"area":"safety"},{"id":"2206.11349","title":"Prompt Injection: Parameterization of Fixed Inputs","created":"2022-05-31","cited_by_count":36,"area":"safety"},{"id":"2410.18210","title":"Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks","created":"2024-10-23","cited_by_count":33,"area":"safety"},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"id":"2402.13148","title":"Defending Jailbreak Prompts via In-Context Adversarial Game","created":"2024-02-20","cited_by_count":29,"area":"safety"},{"id":"2402.15180","title":"Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement","created":"2024-02-23","cited_by_count":29,"area":"safety"},{"id":"2309.13322","title":"From Text to Source: Results in Detecting Large Language Model-Generated Content","created":"2023-09-23","cited_by_count":26,"area":"safety"},{"id":"2309.11830","title":"Goal-Oriented Prompt Attack and Safety Evaluation for LLMs","created":"2023-09-21","cited_by_count":24,"area":"safety"},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2402.14883","title":"Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning","created":"2024-02-22","cited_by_count":21,"area":"safety"},{"id":"2410.14827","title":"Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment","created":"2024-10-18","cited_by_count":21,"area":"safety"},{"id":"2406.10218","title":"Semantic Membership Inference Attack against Large Language Models","created":"2024-06-14","cited_by_count":17,"area":"safety"},{"id":"2501.09798","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","created":"2025-01-16","cited_by_count":17,"area":"safety"},{"id":"2601.02671","title":"Extracting books from production language models","created":"2026-01-06","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":"2412.03235","title":"Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?","created":"2024-12-04","cited_by_count":15,"area":"safety"},{"id":"2404.19597","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","created":"2024-04-30","cited_by_count":14,"area":"safety"},{"id":"2501.14250","title":"Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors","created":"2025-01-24","cited_by_count":13,"area":"safety"},{"id":"2504.03174","title":"Multi-lingual Multi-turn Automated Red Teaming for LLMs","created":"2025-04-04","cited_by_count":13,"area":"safety"},{"id":"2405.07667","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","created":"2024-05-13","cited_by_count":12,"area":"safety"},{"id":"2408.07291","title":"Evaluating LLM-based Personal Information Extraction and Countermeasures","created":"2024-08-14","cited_by_count":12,"area":"safety"},{"id":"2408.09878","title":"Transferring Backdoors between Large Language Models by Knowledge Distillation","created":"2024-08-19","cited_by_count":12,"area":"safety"},{"id":"2503.02174","title":"Adversarial Tokenization","created":"2025-03-04","cited_by_count":11,"area":"safety"},{"id":"2504.07113","title":"How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities","created":"2025-03-20","cited_by_count":11,"area":"safety"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2402.01053","title":"Plan-Grounded Large Language Models for Dual Goal Conversational Settings","created":"2024-02-01","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":"2308.07847","title":"Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models","created":"2023-08-15","cited_by_count":7,"area":"safety"},{"id":"2506.02442","title":"Should LLM Safety Be More Than Refusing Harmful Instructions?","created":"2025-06-03","cited_by_count":7,"area":"safety"},{"id":"2509.01631","title":"Unraveling LLM Jailbreaks Through Safety Knowledge Neurons","created":"2025-09-01","cited_by_count":7,"area":"safety"},{"id":"2510.21910","title":"Adversarial D\\'ej\\`a Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks","created":"2025-10-24","cited_by_count":7,"area":"safety"},{"id":"2601.05445","title":"Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models","created":"2026-01-09","cited_by_count":7,"area":"safety"},{"id":"2504.14738","title":"PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines","created":"2025-04-20","cited_by_count":6,"area":"safety"},{"id":"2510.16629","title":"On the Impossibility of Retrain Equivalence in Machine Unlearning","created":"2025-10-18","cited_by_count":6,"area":"safety"},{"id":"2407.04151","title":"Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers","created":"2024-07-04","cited_by_count":5,"area":"safety"},{"id":"2410.10150","title":"Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting","created":"2024-10-14","cited_by_count":5,"area":"safety"},{"id":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"safety"},{"id":"2503.17953","title":"Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts","created":"2025-03-23","cited_by_count":5,"area":"safety"},{"id":"2505.15674","title":"UniErase: Towards Balanced and Precise Unlearning in Language Models","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2507.06043","title":"CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations","created":"2025-07-08","cited_by_count":5,"area":"safety"},{"id":"2507.15112","title":"Distributional Machine Unlearning via Selective Data Removal","created":"2025-07-20","cited_by_count":5,"area":"safety"},{"id":"2510.02962","title":"Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking","created":"2025-10-03","cited_by_count":5,"area":"safety"},{"id":"2410.04190","title":"Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models","created":"2024-10-05","cited_by_count":4,"area":"safety"},{"id":"2410.21750","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","created":"2024-10-29","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":"2508.15182","title":"SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks","created":"2025-08-21","cited_by_count":4,"area":"safety"},{"id":"2407.14738","title":"Flatness-aware Sequential Learning Generates Resilient Backdoors","created":"2024-07-20","cited_by_count":3,"area":"safety"},{"id":"2601.08490","title":"BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2404.18567","title":"Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks","created":"2024-04-29","cited_by_count":2,"area":"safety"},{"id":"2411.09125","title":"DROJ: A Prompt-Driven Attack against Large Language Models","created":"2024-11-14","cited_by_count":2,"area":"safety"},{"id":"2504.05689","title":"Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2504.19019","title":"Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs","created":"2025-04-26","cited_by_count":2,"area":"safety"},{"id":"2506.10946","title":"GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models","created":"2025-06-12","cited_by_count":2,"area":"safety"},{"id":"2512.23173","title":"EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion","created":"2025-12-29","cited_by_count":2,"area":"safety"},{"id":"2503.12931","title":"MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting","created":"2025-03-17","cited_by_count":1,"area":"safety"},{"id":"2504.06577","title":"Bypassing Safety Guardrails in LLMs Using Humor","created":"2025-04-09","cited_by_count":1,"area":"safety"},{"id":"2509.25843","title":"ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2510.18674","title":"Exploring Membership Inference Vulnerabilities in Clinical Large Language Models","created":"2025-10-21","cited_by_count":1,"area":"safety"},{"id":"2607.27081","title":"On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2502.20952","title":"Efficient Jailbreaking of Large Models by Freeze Training: Lower Layers Exhibit Greater Sensitivity to Harmful Content","created":"2025-02-28","cited_by_count":0,"area":"safety"},{"id":"2505.13819","title":"Fragments to Facts: Partial-Information Fragment Inference from LLMs","created":"2025-05-20","cited_by_count":0,"area":"safety"},{"id":"2510.09471","title":"Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World","created":"2025-10-10","cited_by_count":0,"area":"safety"},{"id":"2512.10766","title":"Metaphor-based Jailbreak Attacks on Text-to-Image Models","created":"2025-12-06","cited_by_count":0,"area":"safety"},{"id":"2601.13359","title":"Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2605.26595","title":"Cordyceps: Covert Control Attacks on LLMs via Data Poisoning","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2606.30263","title":"Defending Against Harmful Supervision Hidden in Benign Samples","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2608.09900","title":"Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2609.09553","title":"Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning","created":"2026-09-09","cited_by_count":0,"area":"safety"}],"next_cursor":null}