{"total":96,"rows":[{"id":"2505.23643","title":"Securing AI Agents with Information-Flow Control","created":"2025-05-29","cited_by_count":121,"area":null},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2408.11491","title":"SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering","created":"2024-08-21","cited_by_count":50,"area":"alignment"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2502.14744","title":"HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States","created":"2025-02-20","cited_by_count":33,"area":"mllm"},{"id":"2505.06311","title":"Defending against Indirect Prompt Injection by Instruction Detection","created":"2025-05-08","cited_by_count":32,"area":"rag"},{"id":"2409.11365","title":"CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration","created":"2024-09-17","cited_by_count":31,"area":"mllm"},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25,"area":"safety"},{"id":"2507.18631","title":"Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment","created":"2025-07-24","cited_by_count":24,"area":"alignment"},{"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":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20,"area":"lr"},{"id":"2406.09250","title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","created":"2024-06-13","cited_by_count":19,"area":"mllm"},{"id":"2410.00296","title":"VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild","created":"2024-10-01","cited_by_count":18,"area":"mllm"},{"id":"2505.14103","title":"AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models","created":"2025-05-20","cited_by_count":18,"area":"safety"},{"id":"2505.00976","title":"Attack and defense techniques in large language models: A survey and new perspectives","created":"2025-05-02","cited_by_count":14,"area":null},{"id":"2509.14558","title":"LLM Jailbreak Detection for (Almost) Free!","created":"2025-09-18","cited_by_count":13,"area":"safety"},{"id":"2412.15289","title":"SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage","created":"2024-12-19","cited_by_count":11,"area":"alignment"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2502.09755","title":"Jailbreak Attack Initializations as Extractors of Compliance Directions","created":"2025-02-13","cited_by_count":10,"area":"safety"},{"id":"2503.04693","title":"UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets","created":"2025-03-06","cited_by_count":10,"area":"safety"},{"id":"2504.03770","title":"JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model","created":"2025-04-03","cited_by_count":10,"area":"mllm"},{"id":"2504.16489","title":"Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate","created":"2025-04-23","cited_by_count":10,"area":"lr"},{"id":"2502.11411","title":"Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2409.19521","title":"GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks","created":"2024-09-29","cited_by_count":7,"area":"safety"},{"id":"2512.05485","title":"TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations","created":"2025-12-05","cited_by_count":7,"area":"safety"},{"id":"2604.17562","title":"SafeAgent: A Runtime Protection Architecture for Agentic Systems","created":"2026-04-19","cited_by_count":7,"area":"agents"},{"id":"2407.09050","title":"Refusing Safe Prompts for Multi-modal Large Language Models","created":"2024-07-12","cited_by_count":6,"area":"mllm"},{"id":"2504.00446","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","created":"2025-04-01","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":"2504.19440","title":"JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift","created":"2025-04-28","cited_by_count":5,"area":"safety"},{"id":"2507.09424","title":"DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models","created":"2025-07-12","cited_by_count":5,"area":null},{"id":"2603.19574","title":"AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?","created":"2026-03-20","cited_by_count":5,"area":null},{"id":"2604.16242","title":"Detecting and Suppressing Reward Hacking with Gradient Fingerprints","created":"2026-04-17","cited_by_count":5,"area":"alignment"},{"id":"2411.01565","title":"SQL Injection Jailbreak: A Structural Disaster of Large Language Models","created":"2024-11-03","cited_by_count":4,"area":"safety"},{"id":"2505.13862","title":"PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2506.12299","title":"QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety","created":"2025-06-14","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":"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":"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":"2601.10543","title":"Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing","created":"2026-01-15","cited_by_count":4,"area":"safety"},{"id":"2603.17372","title":"Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift","created":"2026-03-18","cited_by_count":4,"area":"mllm"},{"id":"2506.16792","title":"MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning","created":"2025-06-20","cited_by_count":3,"area":"safety"},{"id":"2508.14128","title":"CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection","created":"2025-08-19","cited_by_count":3,"area":"safety"},{"id":"2510.17006","title":"Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization","created":"2025-10-19","cited_by_count":3,"area":"safety"},{"id":"2601.03537","title":"STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2601.03600","title":"ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2404.19048","title":"A Framework for Real-time Safeguarding the Text Generation of Large Language Model","created":"2024-04-29","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":"2508.09201","title":"Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models","created":"2025-08-08","cited_by_count":2,"area":"mllm"},{"id":"2602.16977","title":"Fail-Closed Alignment for Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"alignment"},{"id":"2603.27332","title":"Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2604.00310","title":"CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment","created":"2026-03-31","cited_by_count":2,"area":"alignment"},{"id":"2604.08297","title":"Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models","created":"2026-04-09","cited_by_count":2,"area":"safety"},{"id":"2604.09222","title":"GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking","created":"2026-04-10","cited_by_count":2,"area":"safety"},{"id":"2604.18775","title":"An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models","created":"2026-04-20","cited_by_count":2,"area":"safety"},{"id":"2604.26167","title":"Test-Time Safety Alignment","created":"2026-04-28","cited_by_count":2,"area":"alignment"},{"id":"2605.24817","title":"RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry","created":"2026-05-24","cited_by_count":2,"area":"moe"},{"id":"2607.09697","title":"Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs","created":"2026-06-20","cited_by_count":2,"area":"mllm"},{"id":"2608.23959","title":"NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution","created":"2026-08-25","cited_by_count":2,"area":"alignment"},{"id":"2408.11308","title":"Defending against Jailbreak through Early Exit Generation of Large Language Models","created":"2024-08-21","cited_by_count":1,"area":"inference"},{"id":"2505.05619","title":"LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities","created":"2025-05-08","cited_by_count":1,"area":"safety"},{"id":"2505.16526","title":"EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance","created":"2025-05-22","cited_by_count":1,"area":"mechinterp"},{"id":"2510.15430","title":"Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models","created":"2025-10-17","cited_by_count":1,"area":"mllm"},{"id":"2511.00509","title":"Reimagining Safety Alignment with An Image","created":"2025-11-01","cited_by_count":1,"area":"alignment"},{"id":"2512.03356","title":"From static to adaptive: immune memory-based jailbreak detection for large language models","created":"2025-12-03","cited_by_count":1,"area":"safety"},{"id":"2512.11783","title":"Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2605.02921","title":"EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models","created":"2026-04-22","cited_by_count":1,"area":"safety"},{"id":"2606.00160","title":"DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.04867","title":"AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2608.14303","title":"Detecting Contaminated Code-Generation Prompt Batches via Influence Functions","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.16852","title":"What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2609.21793","title":"CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation","created":"2026-09-18","cited_by_count":1,"area":"safety"},{"id":"2609.26185","title":"Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs","created":"2026-08-10","cited_by_count":1,"area":"safety"},{"id":"2507.19185","title":"PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.11290","title":"SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering","created":"2025-08-15","cited_by_count":0,"area":"safety"},{"id":"2511.18933","title":"Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2601.03005","title":"JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification","created":"2026-01-06","cited_by_count":0,"area":"alignment"},{"id":"2602.04893","title":"A Causal Perspective for Enhancing Jailbreak Attack and Defense","created":"2026-01-31","cited_by_count":0,"area":"safety"},{"id":"2602.13321","title":"Detecting Jailbreak Attempts in Clinical Training LLMs Through Automated Linguistic Feature Extraction","created":"2026-02-10","cited_by_count":0,"area":"safety"},{"id":"2602.17696","title":"Can LLM Safety Be Ensured by Constraining Parameter Regions?","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2602.19396","title":"Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement","created":"2026-02-23","cited_by_count":0,"area":"safety"},{"id":"2604.01473","title":"SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits","created":"2026-04-01","cited_by_count":0,"area":"safety"},{"id":"2604.05179","title":"Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering","created":"2026-04-06","cited_by_count":0,"area":"safety"},{"id":"2604.08577","title":"Distributionally Robust Token Optimization in RLHF","created":"2026-03-27","cited_by_count":0,"area":"alignment"},{"id":"2605.02958","title":"Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection","created":"2026-05-02","cited_by_count":0,"area":"safety"},{"id":"2605.03095","title":"Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses","created":"2026-05-04","cited_by_count":0,"area":"safety"},{"id":"2605.19321","title":"Exploring and Developing a Pre-Model Safeguard with Draft Models","created":"2026-05-19","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":"2608.09624","title":"Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2609.05850","title":"SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement","created":"2026-09-05","cited_by_count":0,"area":"alignment"},{"id":"2609.21484","title":"HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.36849","title":"Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.02092","title":"Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}