{"total":92,"rows":[{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136,"area":null},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126,"area":null},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58,"area":null},{"id":"2407.11438","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","created":"2024-07-16","cited_by_count":47,"area":null},{"id":"2412.13879","title":"Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings","created":"2024-12-18","cited_by_count":35,"area":null},{"id":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2404.17120","title":"Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs","created":"2024-04-26","cited_by_count":11,"area":null},{"id":"2507.06256","title":"Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2510.04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","created":"2025-10-05","cited_by_count":9,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2603.01919","title":"Real Money, Fake Models: Deceptive Model Claims in Shadow APIs","created":"2026-03-02","cited_by_count":8,"area":null},{"id":"2501.19040","title":"Towards the Worst-case Robustness of Large Language Models","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2502.19320","title":"Shh, don't say that! Domain Certification in LLMs","created":"2025-02-26","cited_by_count":7,"area":null},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2510.01529","title":"Bypassing Prompt Guards in Production with Controlled-Release Prompting","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2602.05910","title":"Chunky Post-Training: Data Driven Failures of Generalization","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2501.00745","title":"Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines","created":"2025-01-01","cited_by_count":5,"area":null},{"id":"2502.04643","title":"Confidence Elicitation: A New Attack Vector for Large Language Models","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2407.12999","title":"Securing the Future of GenAI: Policy and Technology","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2505.18003","title":"An Example Safety Case for Safeguards Against Misuse","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2605.26156","title":"Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2503.17388","title":"AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2602.11528","title":"Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2604.17730","title":"MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2410.13138","title":"Data Defenses Against Large Language Models","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2501.01741","title":"How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2504.06669","title":"NLP Security and Ethics, in the Wild","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2505.14226","title":"Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2506.06273","title":"AdvSumm: Adversarial Training for Bias Mitigation in Text Summarization","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2508.15858","title":"Building and Measuring Trust between Large Language Models","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2602.05656","title":"Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation","created":"2026-02-05","cited_by_count":2,"area":null},{"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":"2604.23099","title":"ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.14553","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2606.02822","title":"Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.28929","title":"Cybersecurity is the True Frontier for Generative AI Success or Failure","created":"2026-06-27","cited_by_count":2,"area":null},{"id":"2410.21597","title":"Reducing the Scope of Language Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2504.20310","title":"A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2505.14015","title":"AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.18680","title":"$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.23296","title":"Securing AI Systems: A Guide to Known Attacks and Impacts","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.06111","title":"SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2511.09287","title":"From Model Training to Model Raising","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2601.01627","title":"JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2602.00305","title":"Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.22291","title":"Manifold of Failure: Behavioral Attraction Basins in Language Models","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2605.12813","title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.15118","title":"Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.19605","title":"FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2403.18205","title":"Exploring the Privacy Protection Capabilities of Chinese Large Language Models","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.14943","title":"Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.20471","title":"Probing AI Safety with Source Code","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2507.02057","title":"MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.02074","title":"The SMeL Test: A simple benchmark for media literacy in language models","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2512.03720","title":"Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2602.23117","title":"Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.07286","title":"Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.06266","title":"Attribution-Driven Explainable Intrusion Detection with Encoder-Based Large Language Models","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.12500","title":"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.11029","title":"FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.15152","title":"Widening the Gap: Exploiting LLM Quantization via Outlier Injection","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.17288","title":"When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.30521","title":"Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.12439","title":"Position: Generative Engine Optimization Creates Underexamined Risks, Governance Must Target Concentration, Disclosure, and Academic Blind Spots","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.01859","title":"Safety Targeted Embedding Exploit via Refinement","created":"2026-07-02","cited_by_count":0,"area":null},{"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":"2608.18093","title":"Abliteration Mitigation via Refusal Aliases","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2608.20392","title":"Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.31105","title":"BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.08399","title":"MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.15383","title":"Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26175","title":"EADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35117","title":"Tool Mediation Alters Refusal Mechanisms in Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36477","title":"Guard Models Are Overconfident Where Base Models Are Uncertain","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}