{"total":108,"rows":[{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264,"area":"safety"},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"area":"safety"},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"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":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134,"area":"safety"},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110,"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":"2308.00113","title":"Three Bricks to Consolidate Watermarks for Large Language Models","created":"2023-07-26","cited_by_count":84,"area":"safety"},{"id":"2506.12618","title":"OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics","created":"2025-06-14","cited_by_count":83,"area":"safety"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2310.07676","title":"Composite Backdoor Attacks Against Large Language Models","created":"2023-10-11","cited_by_count":73,"area":"safety"},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68,"area":"safety"},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67,"area":"safety"},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62,"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":"2308.01990","title":"From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?","created":"2023-08-03","cited_by_count":55,"area":"safety"},{"id":"2402.14872","title":"Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs","created":"2024-02-21","cited_by_count":53,"area":"safety"},{"id":"2402.15911","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","created":"2024-02-24","cited_by_count":52,"area":"safety"},{"id":"2401.16820","title":"Provably Robust Multi-bit Watermarking for AI-generated Text","created":"2024-01-30","cited_by_count":47,"area":"safety"},{"id":"2406.12038","title":"Soft Prompting for Unlearning in Large Language Models","created":"2024-06-17","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":"2311.00172","title":"Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield","created":"2023-10-31","cited_by_count":25,"area":"safety"},{"id":"2312.04127","title":"Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak","created":"2023-12-07","cited_by_count":23,"area":"safety"},{"id":"2406.05344","title":"MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention","created":"2024-06-08","cited_by_count":20,"area":"safety"},{"id":"2411.12701","title":"When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations","created":"2024-11-19","cited_by_count":20,"area":"safety"},{"id":"2409.14729","title":"PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs","created":"2024-09-23","cited_by_count":17,"area":"safety"},{"id":"2412.08615","title":"Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models","created":"2024-12-11","cited_by_count":15,"area":"safety"},{"id":"2502.10525","title":"Towards Watermarking of Open-Source LLMs","created":"2025-02-14","cited_by_count":13,"area":"safety"},{"id":"2509.14558","title":"LLM Jailbreak Detection for (Almost) Free!","created":"2025-09-18","cited_by_count":13,"area":"safety"},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2407.01376","title":"Badllama 3: removing safety finetuning from Llama 3 in minutes","created":"2024-07-01","cited_by_count":11,"area":"safety"},{"id":"2502.18511","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","created":"2025-02-22","cited_by_count":11,"area":"safety"},{"id":"2308.13449","title":"The Poison of Alignment","created":"2023-08-25","cited_by_count":10,"area":"safety"},{"id":"2408.10668","title":"Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation","created":"2024-08-20","cited_by_count":10,"area":"safety"},{"id":"2410.22143","title":"AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts","created":"2024-10-29","cited_by_count":10,"area":"safety"},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9,"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":"2408.10722","title":"MEGen: Generative Backdoor into Large Language Models via Model Editing","created":"2024-08-20","cited_by_count":8,"area":"safety"},{"id":"2409.15361","title":"Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning","created":"2024-09-18","cited_by_count":8,"area":"safety"},{"id":"2503.15128","title":"Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors","created":"2025-03-19","cited_by_count":8,"area":"safety"},{"id":"2512.07375","title":"LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples","created":"2025-12-08","cited_by_count":8,"area":"safety"},{"id":"2406.19395","title":"Dataset Size Recovery from LoRA Weights","created":"2024-06-27","cited_by_count":7,"area":"safety"},{"id":"2408.08924","title":"Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks","created":"2024-08-15","cited_by_count":6,"area":"safety"},{"id":"2408.17354","title":"Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage","created":"2024-08-30","cited_by_count":6,"area":"safety"},{"id":"2503.05445","title":"Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks","created":"2025-03-07","cited_by_count":6,"area":"safety"},{"id":"2312.14923","title":"Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models","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":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"area":"safety"},{"id":"2505.16567","title":"Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning","created":"2025-05-22","cited_by_count":5,"area":"safety"},{"id":"2601.02680","title":"Adversarial Contrastive Learning for LLM Quantization Attacks","created":"2026-01-06","cited_by_count":5,"area":"safety"},{"id":"2405.19563","title":"Unlearning Climate Misinformation in Large Language Models","created":"2024-05-29","cited_by_count":4,"area":"safety"},{"id":"2510.23891","title":"PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2606.06946","title":"Auditing Training Data in Domain-adapted LLMs: LoRA-MINT","created":"2026-06-05","cited_by_count":4,"area":"safety"},{"id":"2505.23015","title":"Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models","created":"2025-05-29","cited_by_count":3,"area":"safety"},{"id":"2506.15975","title":"Multi-use LLM Watermarking and the False Detection Problem","created":"2025-06-19","cited_by_count":3,"area":"safety"},{"id":"2507.17259","title":"Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs","created":"2025-07-23","cited_by_count":3,"area":"safety"},{"id":"2512.16292","title":"In-Context Probing for Membership Inference in Fine-Tuned Language Models","created":"2025-12-18","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":"2508.12622","title":"Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes","created":"2025-08-18","cited_by_count":2,"area":"safety"},{"id":"2605.12765","title":"Inference-Time Machine Unlearning via Gated Activation Redirection","created":"2026-05-12","cited_by_count":2,"area":"safety"},{"id":"2607.12792","title":"Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels","created":"2026-07-14","cited_by_count":2,"area":"safety"},{"id":"2412.06846","title":"Classifier-free guidance in LLMs Safety","created":"2024-12-08","cited_by_count":1,"area":"safety"},{"id":"2505.24252","title":"A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming","created":"2025-05-30","cited_by_count":1,"area":"safety"},{"id":"2506.14474","title":"LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2510.01494","title":"Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2512.14751","title":"One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs","created":"2025-12-14","cited_by_count":1,"area":"safety"},{"id":"2601.15538","title":"QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs","created":"2026-01-21","cited_by_count":1,"area":"safety"},{"id":"2602.23400","title":"U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation","created":"2026-02-26","cited_by_count":1,"area":"safety"},{"id":"2605.02196","title":"DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning","created":"2026-05-04","cited_by_count":1,"area":"safety"},{"id":"2605.15138","title":"Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution","created":"2026-05-14","cited_by_count":1,"area":"safety"},{"id":"2605.20641","title":"Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs","created":"2026-05-20","cited_by_count":1,"area":"safety"},{"id":"2606.20553","title":"From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2606.27210","title":"Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes","created":"2026-06-25","cited_by_count":1,"area":"safety"},{"id":"2608.22246","title":"N\\\"urnberg NLP @ GermEval Shared Task 2026: Harmful Content Detection in German Social Media through Error-Independent LLM Voters","created":"2026-08-23","cited_by_count":1,"area":"safety"},{"id":"2408.10334","title":"A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers","created":"2024-08-19","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":"2510.13901","title":"RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs","created":"2025-10-14","cited_by_count":0,"area":"safety"},{"id":"2601.00454","title":"Defensive M2S: Training Guardrail Models on Compressed Multi-turn Conversations","created":"2026-01-01","cited_by_count":0,"area":"safety"},{"id":"2604.07835","title":"Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation","created":"2026-04-09","cited_by_count":0,"area":"safety"},{"id":"2604.10326","title":"Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion","created":"2026-04-11","cited_by_count":0,"area":"safety"},{"id":"2604.21571","title":"Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies","created":"2026-04-23","cited_by_count":0,"area":"safety"},{"id":"2605.01699","title":"Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance","created":"2026-05-03","cited_by_count":0,"area":"safety"},{"id":"2605.08898","title":"LLM-Agnostic Semantic Representation Attack","created":"2026-05-09","cited_by_count":0,"area":"safety"},{"id":"2605.10176","title":"When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.11612","title":"When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2606.09388","title":"Distilling Safe LLM Systems via Soft Prompts for On Device Settings","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2606.17123","title":"LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2606.28962","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","created":"2026-06-27","cited_by_count":0,"area":"safety"},{"id":"2607.13088","title":"Securing LLMs in the Wild: Privacy and Security Challenges at the Edge","created":"2026-07-13","cited_by_count":0,"area":"safety"},{"id":"2607.25451","title":"Bits and Memories: Measuring Verbatim Extraction Across LLM Quantization","created":"2026-07-28","cited_by_count":0,"area":"safety"},{"id":"2608.06795","title":"LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes","created":"2026-08-07","cited_by_count":0,"area":"safety"},{"id":"2608.11348","title":"An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs","created":"2026-08-11","cited_by_count":0,"area":"safety"},{"id":"2608.21895","title":"Breaking the Assumptions: Auditing Input-Side Jailbreak Defenses Against Semantic Attacks","created":"2026-08-22","cited_by_count":0,"area":"safety"},{"id":"2608.24354","title":"Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs","created":"2026-08-25","cited_by_count":0,"area":"safety"},{"id":"2608.25605","title":"From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2608.26506","title":"A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2608.27512","title":"Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap","created":"2026-08-27","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}