{"total":67,"rows":[{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672,"area":"safety"},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2312.17673","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","created":"2023-12-29","cited_by_count":106,"area":"safety"},{"id":"2403.03792","title":"Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks","created":"2024-03-06","cited_by_count":85,"area":"safety"},{"id":"2308.10819","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","created":"2023-08-17","cited_by_count":59,"area":"safety"},{"id":"2403.02817","title":"Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications","created":"2024-03-05","cited_by_count":59,"area":"safety"},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30,"area":"safety"},{"id":"2406.03589","title":"Ranking Manipulation for Conversational Search Engines","created":"2024-06-05","cited_by_count":26,"area":"safety"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2402.05864","title":"Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs","created":"2024-02-08","cited_by_count":22,"area":"safety"},{"id":"2402.02160","title":"Data Poisoning for In-context Learning","created":"2024-02-03","cited_by_count":21,"area":"safety"},{"id":"2501.16466","title":"Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks","created":"2025-01-27","cited_by_count":17,"area":"safety"},{"id":"2410.03537","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","created":"2024-10-04","cited_by_count":16,"area":"safety"},{"id":"2601.07072","title":"Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems","created":"2026-01-11","cited_by_count":16,"area":"safety"},{"id":"2507.06908","title":"MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection","created":"2025-07-09","cited_by_count":15,"area":"safety"},{"id":"2504.07467","title":"Defense against Prompt Injection Attacks via Mixture of Encodings","created":"2025-04-10","cited_by_count":14,"area":"safety"},{"id":"2411.06899","title":"LongSafety: Enhance Safety for Long-Context LLMs","created":"2024-11-11","cited_by_count":11,"area":"safety"},{"id":"2408.11749","title":"Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks","created":"2024-08-21","cited_by_count":10,"area":"safety"},{"id":"2411.11407","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","created":"2024-11-18","cited_by_count":10,"area":"safety"},{"id":"2502.09755","title":"Jailbreak Attack Initializations as Extractors of Compliance Directions","created":"2025-02-13","cited_by_count":10,"area":"safety"},{"id":"2506.05314","title":"Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2511.05797","title":"When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins","created":"2025-11-08","cited_by_count":9,"area":"safety"},{"id":"2502.08142","title":"Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences","created":"2025-02-12","cited_by_count":8,"area":"safety"},{"id":"2505.15753","title":"Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval","created":"2025-05-21","cited_by_count":7,"area":"safety"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"area":"safety"},{"id":"2407.14644","title":"Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context","created":"2024-07-19","cited_by_count":6,"area":"safety"},{"id":"2408.01452","title":"Building a Domain-specific Guardrail Model in Production","created":"2024-07-24","cited_by_count":6,"area":"safety"},{"id":"2507.04531","title":"DP-Fusion: Token-Level Differentially Private Inference for Large Language Models","created":"2025-07-06","cited_by_count":6,"area":"safety"},{"id":"2304.14364","title":"CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants","created":"2023-04-27","cited_by_count":5,"area":"safety"},{"id":"2406.12800","title":"Supporting Human Raters with the Detection of Harmful Content using Large Language Models","created":"2024-06-18","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":"2406.10847","title":"TorchOpera: A Compound AI System for LLM Safety","created":"2024-06-16","cited_by_count":4,"area":"safety"},{"id":"2510.12119","title":"ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation","created":"2025-10-14","cited_by_count":4,"area":"safety"},{"id":"2601.04740","title":"StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation","created":"2026-01-08","cited_by_count":4,"area":"safety"},{"id":"2510.17620","title":"Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2601.08490","title":"BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2605.29237","title":"Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking","created":"2026-05-28","cited_by_count":3,"area":"safety"},{"id":"2606.10813","title":"RedAct: Redacting Agent Capability Traces for Procedural Skill Protection","created":"2026-06-09","cited_by_count":3,"area":"safety"},{"id":"2503.08990","title":"Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks","created":"2025-03-12","cited_by_count":2,"area":"safety"},{"id":"2508.16484","title":"HAMSA: Hijacking Aligned Compact Models via Stealthy Automation","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2604.15579","title":"Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents","created":"2026-04-16","cited_by_count":2,"area":"safety"},{"id":"2607.00605","title":"Auditing Forgetting in Limited Memory Language Models","created":"2026-07-01","cited_by_count":2,"area":"safety"},{"id":"2607.22024","title":"Agent Security Needs Redefinition through a Holistic Framework","created":"2026-07-24","cited_by_count":2,"area":"safety"},{"id":"2405.04756","title":"Red-Teaming for Inducing Societal Bias in Large Language Models","created":"2024-05-08","cited_by_count":1,"area":"safety"},{"id":"2504.02486","title":"We Need Improved Data Curation and Attribution in AI for Scientific Discovery","created":"2025-04-03","cited_by_count":1,"area":"safety"},{"id":"2510.09689","title":"When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models","created":"2025-10-09","cited_by_count":1,"area":"safety"},{"id":"2602.00750","title":"Bypassing Prompt Injection Detectors through Evasive Injections","created":"2026-01-31","cited_by_count":1,"area":"safety"},{"id":"2606.01513","title":"Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense","created":"2026-06-01","cited_by_count":1,"area":"safety"},{"id":"2412.06788","title":"Poison Attacks and Adversarial Prompts Against an Informed University Virtual Assistant","created":"2024-11-03","cited_by_count":0,"area":"safety"},{"id":"2506.13028","title":"NaSh: Guardrails for an LLM-Powered Natural Language Shell","created":"2025-06-16","cited_by_count":0,"area":"safety"},{"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":"2601.15331","title":"RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models","created":"2026-01-20","cited_by_count":0,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2604.16606","title":"SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models","created":"2026-04-17","cited_by_count":0,"area":"safety"},{"id":"2604.25247","title":"R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models","created":"2026-04-28","cited_by_count":0,"area":"safety"},{"id":"2605.01047","title":"LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.01758","title":"Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems","created":"2026-05-03","cited_by_count":0,"area":"safety"},{"id":"2605.18133","title":"An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments","created":"2026-05-18","cited_by_count":0,"area":"safety"},{"id":"2605.19147","title":"Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks","created":"2026-05-18","cited_by_count":0,"area":"safety"},{"id":"2606.04612","title":"Hybrid Adversarial Defence for Natural Language Understanding Tasks","created":"2026-06-03","cited_by_count":0,"area":"safety"},{"id":"2606.05787","title":"SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2606.19660","title":"A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots","created":"2026-06-17","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":"2608.28361","title":"GRACE:Gradient-guided Coreset Selection for LLM Unlearning","created":"2026-08-28","cited_by_count":0,"area":"safety"},{"id":"2610.02817","title":"RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models","created":"2026-10-02","cited_by_count":0,"area":"safety"},{"id":"2610.04860","title":"Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate","created":"2026-10-04","cited_by_count":0,"area":"safety"},{"id":"2610.19133","title":"TRACER: Trace-Regularized Training Against Indirect Prompt Injection","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}