{"total":106,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2502.11054","title":"Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-02-16","cited_by_count":64,"area":"lr"},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56,"area":"alignment"},{"id":"2503.23674","title":"Large Language Models Pass the Turing Test","created":"2025-03-31","cited_by_count":48,"area":null},{"id":"2504.07717","title":"PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization","created":"2025-04-10","cited_by_count":32,"area":"rag"},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2512.07086","title":"ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking","created":"2025-12-08","cited_by_count":23,"area":"lr"},{"id":"2411.08410","title":"The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense","created":"2024-11-13","cited_by_count":21,"area":"safety"},{"id":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18,"area":"safety"},{"id":"2502.04951","title":"Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search","created":"2025-02-07","cited_by_count":16,"area":null},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14,"area":"safety"},{"id":"2408.11727","title":"Efficient Detection of Toxic Prompts in Large Language Models","created":"2024-08-21","cited_by_count":13,"area":null},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2507.07341","title":"On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment","created":"2025-07-09","cited_by_count":12,"area":"safety"},{"id":"2404.04849","title":"Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection","created":"2024-04-07","cited_by_count":9,"area":"safety"},{"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":"2506.07121","title":"Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models","created":"2025-06-08","cited_by_count":9,"area":"safety"},{"id":"2507.11630","title":"Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility","created":"2025-07-15","cited_by_count":9,"area":"safety"},{"id":"2408.09326","title":"Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks","created":"2024-08-18","cited_by_count":8,"area":"safety"},{"id":"2411.07238","title":"OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model","created":"2024-11-11","cited_by_count":8,"area":null},{"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":"2505.04345","title":"Build Agent Advocates, Not Platform Agents","created":"2025-05-07","cited_by_count":8,"area":"agents"},{"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":"2502.00735","title":"`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs","created":"2025-02-02","cited_by_count":7,"area":"safety"},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","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":"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":"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":"2505.01065","title":"Good News for Script Kiddies? Evaluating Large Language Models for Automated Exploit Generation","created":"2025-05-02","cited_by_count":6,"area":null},{"id":"2508.11222","title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","created":"2025-08-15","cited_by_count":6,"area":"safety"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2505.07532","title":"RAI: Flexible Agent Framework for Embodied AI","created":"2025-05-12","cited_by_count":5,"area":"agents"},{"id":"2505.09602","title":"Adversarial Suffix Filtering: a Defense Pipeline for LLMs","created":"2025-05-14","cited_by_count":5,"area":"safety"},{"id":"2505.17519","title":"Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives","created":"2025-05-23","cited_by_count":5,"area":"safety"},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2510.15476","title":"SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses","created":"2025-10-17","cited_by_count":5,"area":"safety"},{"id":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"},{"id":"2604.09747","title":"ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying","created":"2026-04-10","cited_by_count":5,"area":"agents"},{"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":"2411.01565","title":"SQL Injection Jailbreak: A Structural Disaster of Large Language Models","created":"2024-11-03","cited_by_count":4,"area":"safety"},{"id":"2411.19211","title":"On the Ethical Considerations of Generative Agents","created":"2024-11-28","cited_by_count":4,"area":"agents"},{"id":"2501.15693","title":"Beyond Benchmarks: On The False Promise of AI Regulation","created":"2025-01-26","cited_by_count":4,"area":null},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2503.24191","title":"When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output","created":"2025-03-31","cited_by_count":4,"area":"safety"},{"id":"2406.02044","title":"Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA","created":"2024-06-04","cited_by_count":3,"area":"safety"},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"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":"2507.06489","title":"On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2508.16921","title":"Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.17277","title":"PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2512.20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2601.18827","title":"Automated structural testing of LLM-based agents: methods, framework, and case studies","created":"2026-01-25","cited_by_count":3,"area":"agents"},{"id":"2604.21159","title":"Adaptive Instruction Composition for Automated LLM Red-Teaming","created":"2026-04-22","cited_by_count":3,"area":"safety"},{"id":"2605.03441","title":"Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis","created":"2026-05-05","cited_by_count":3,"area":"safety"},{"id":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"id":"2606.00105","title":"Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning","created":"2026-05-26","cited_by_count":3,"area":"mllm"},{"id":"2412.20087","title":"On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2501.08814","title":"SAIF: A Comprehensive Framework for Evaluating the Risks of Generative AI in the Public Sector","created":"2025-01-15","cited_by_count":2,"area":"safety"},{"id":"2504.04373","title":"StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformation","created":"2025-04-06","cited_by_count":2,"area":null},{"id":"2506.11402","title":"LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2512.18244","title":"Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation","created":"2025-12-20","cited_by_count":2,"area":"safety"},{"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":"2410.06462","title":"Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders","created":"2024-10-09","cited_by_count":1,"area":"safety"},{"id":"2410.24178","title":"AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2503.03502","title":"Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension","created":"2025-03-05","cited_by_count":1,"area":"safety"},{"id":"2506.11521","title":"Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models","created":"2025-06-13","cited_by_count":1,"area":"mllm"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"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":"2509.06807","title":"MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security","created":"2025-09-08","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":"2509.16060","title":"SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection","created":"2025-09-19","cited_by_count":1,"area":"alignment"},{"id":"2509.16870","title":"DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems","created":"2025-09-21","cited_by_count":1,"area":"safety"},{"id":"2510.01644","title":"Machine Learning for Detection and Analysis of Novel LLM Jailbreaks","created":"2025-10-02","cited_by_count":1,"area":"safety"},{"id":"2512.19016","title":"DREAM: Dynamic Red-teaming across Environments for AI Models","created":"2025-12-22","cited_by_count":1,"area":"agents"},{"id":"2512.21236","title":"Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2601.09321","title":"SpatialJB: How Text Distribution Art Becomes the \"Jailbreak Key\" for LLM Guardrails","created":"2026-01-14","cited_by_count":1,"area":"safety"},{"id":"2603.25164","title":"PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2026-03-26","cited_by_count":1,"area":"rag"},{"id":"2604.11309","title":"The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems","created":"2026-04-13","cited_by_count":1,"area":"safety"},{"id":"2605.01899","title":"Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment","created":"2026-05-03","cited_by_count":1,"area":"alignment"},{"id":"2605.08427","title":"The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2608.01117","title":"SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks","created":"2026-08-02","cited_by_count":1,"area":"safety"},{"id":"2507.12185","title":"Jailbreaking Generative AI: Multivector Phishing Threats and Transformer based Defenses","created":"2025-07-16","cited_by_count":0,"area":"safety"},{"id":"2508.02312","title":"Data Security in Large Language Models: Risks, Defense, and Directions","created":"2025-08-04","cited_by_count":0,"area":"safety"},{"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":"2602.04294","title":"How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2603.00369","title":"Policy Compliance of User Requests in Natural Language for AI Systems","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.20833","title":"AVISE: Framework for Evaluating the Security of AI Systems","created":"2026-04-22","cited_by_count":0,"area":"safety"},{"id":"2605.05116","title":"On the Hardness of Junking LLMs","created":"2026-05-06","cited_by_count":0,"area":"safety"},{"id":"2606.00150","title":"Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models","created":"2026-05-29","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":"2606.15503","title":"Synthetic Counteradaptation: A Principle of Human-AI Co-evolution","created":"2026-03-31","cited_by_count":0,"area":null}],"next_cursor":"100"}