{"total":74,"rows":[{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230,"area":"safety"},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2401.12087","title":"Revisiting Demonstration Selection Strategies in In-Context Learning","created":"2024-01-22","cited_by_count":58,"area":null},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2410.12855","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","created":"2024-10-11","cited_by_count":47,"area":"agents"},{"id":"2405.20099","title":"Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks","created":"2024-05-30","cited_by_count":37,"area":"safety"},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","created":"2024-06-13","cited_by_count":31,"area":"safety"},{"id":"2412.17034","title":"Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models","created":"2024-12-22","cited_by_count":23,"area":"safety"},{"id":"2505.15420","title":"Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries","created":"2025-05-21","cited_by_count":19,"area":"rag"},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14,"area":"safety"},{"id":"2506.12707","title":"SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression","created":"2025-06-15","cited_by_count":13,"area":"inference"},{"id":"2508.16347","title":"Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs","created":"2025-08-22","cited_by_count":11,"area":"lr"},{"id":"2505.02862","title":"Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs","created":"2025-05-03","cited_by_count":9,"area":"safety"},{"id":"2505.12060","title":"Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement","created":"2025-05-17","cited_by_count":8,"area":"safety"},{"id":"2411.07559","title":"Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models","created":"2024-11-12","cited_by_count":7,"area":"mllm"},{"id":"2510.05052","title":"Proactive defense against LLM Jailbreak","created":"2025-10-06","cited_by_count":7,"area":"alignment"},{"id":"2602.12418","title":"Sparse Autoencoders are Capable LLM Jailbreak Mitigators","created":"2026-02-12","cited_by_count":6,"area":"safety"},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"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":"2505.24519","title":"AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders","created":"2025-05-30","cited_by_count":5,"area":"mllm"},{"id":"2505.14607","title":"sudoLLM: On Multi-role Alignment of Language Models","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2505.18556","title":"Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation","created":"2025-05-24","cited_by_count":4,"area":"safety"},{"id":"2508.04204","title":"ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments","created":"2025-08-06","cited_by_count":4,"area":"lr"},{"id":"2508.12072","title":"Mitigating Jailbreaks with Intent-Aware LLMs","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2601.03594","title":"Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2602.13547","title":"AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks","created":"2026-02-14","cited_by_count":3,"area":"safety"},{"id":"2412.10423","title":"Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM","created":"2024-12-10","cited_by_count":2,"area":"safety"},{"id":"2502.14486","title":"How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2506.07356","title":"Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks","created":"2025-06-09","cited_by_count":2,"area":"safety"},{"id":"2507.07146","title":"Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak","created":"2025-07-09","cited_by_count":2,"area":"safety"},{"id":"2508.02997","title":"CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors","created":"2025-08-05","cited_by_count":2,"area":"safety"},{"id":"2602.07517","title":"MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2602.09319","title":"Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation","created":"2026-02-10","cited_by_count":2,"area":"rag"},{"id":"2602.16977","title":"Fail-Closed Alignment for Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2504.13052","title":"GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms","created":"2025-04-17","cited_by_count":1,"area":"safety"},{"id":"2508.03054","title":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2508.16406","title":"Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models","created":"2025-08-22","cited_by_count":1,"area":"rag"},{"id":"2512.21110","title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2602.05386","title":"Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2603.16207","title":"Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2604.18946","title":"Reasoning Structure Matters for Safety Alignment of Reasoning Models","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"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":"2607.01277","title":"Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety","created":"2026-07-01","cited_by_count":1,"area":"safety"},{"id":"2506.23423","title":"TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2508.15648","title":"SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models","created":"2025-08-21","cited_by_count":0,"area":"safety"},{"id":"2509.26345","title":"SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2510.20129","title":"SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models","created":"2025-10-23","cited_by_count":0,"area":"alignment"},{"id":"2512.04841","title":"SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security","created":"2025-12-04","cited_by_count":0,"area":"safety"},{"id":"2512.15081","title":"Quantifying Return on Security Controls in LLM Systems","created":"2025-12-17","cited_by_count":0,"area":"safety"},{"id":"2604.15789","title":"A Systematic Study of Training-Free Methods for Trustworthy Large Language Models","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2605.24552","title":"Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2605.26409","title":"Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2605.27375","title":"LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2606.22495","title":"Grounded Scaling: Why Agentic AI Needs Deterministic Environments","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2607.24392","title":"When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2607.26820","title":"Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.13304","title":"Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety","created":"2026-08-13","cited_by_count":0,"area":"safety"},{"id":"2608.30748","title":"The Fragility of Jailbreak Robustness Across Operational States","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.06540","title":"SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure","created":"2026-09-06","cited_by_count":0,"area":"safety"},{"id":"2609.18515","title":"Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models","created":"2026-09-16","cited_by_count":0,"area":"alignment"},{"id":"2610.04470","title":"Reactivating Alignment: Defending LLMs from Jailbreaks via Intention-Aware Input-Output Matching","created":"2026-10-03","cited_by_count":0,"area":"safety"},{"id":"2610.16312","title":"Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}