{"total":33,"rows":[{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264,"area":"safety"},{"id":"2311.07689","title":"MART: Improving LLM Safety with Multi-round Automatic Red-Teaming","created":"2023-11-13","cited_by_count":163,"area":"safety"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110,"area":"safety"},{"id":"2311.04378","title":"Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models","created":"2023-11-07","cited_by_count":87,"area":"safety"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2308.01990","title":"From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?","created":"2023-08-03","cited_by_count":55,"area":"safety"},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54,"area":"safety"},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39,"area":"safety"},{"id":"2405.14189","title":"Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization","created":"2024-05-23","cited_by_count":16,"area":"safety"},{"id":"2506.16349","title":"Watermarking Autoregressive Image Generation","created":"2025-06-19","cited_by_count":16,"area":"safety"},{"id":"2411.11683","title":"Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation","created":"2024-11-18","cited_by_count":15,"area":"safety"},{"id":"2404.19597","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","created":"2024-04-30","cited_by_count":14,"area":"safety"},{"id":"2505.13541","title":"SPIRIT: Patching Speech Language Models against Jailbreak Attacks","created":"2025-05-18","cited_by_count":9,"area":"safety"},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9,"area":"safety"},{"id":"2510.07835","title":"MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation","created":"2025-10-09","cited_by_count":8,"area":"safety"},{"id":"2504.14738","title":"PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines","created":"2025-04-20","cited_by_count":6,"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":"2606.12747","title":"Prefill Awareness in Large Language Models","created":"2026-06-10","cited_by_count":4,"area":"safety"},{"id":"2409.04822","title":"Exploring Straightforward Conversational Red-Teaming","created":"2024-09-07","cited_by_count":3,"area":"safety"},{"id":"2410.02220","title":"Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks","created":"2024-10-03","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":"2601.08490","title":"BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2602.04581","title":"Trust The Typical","created":"2026-02-04","cited_by_count":3,"area":"safety"},{"id":"2602.12318","title":"Abstractive Red-Teaming of Language Model Character","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2605.15172","title":"MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs","created":"2026-05-14","cited_by_count":1,"area":"safety"},{"id":"2507.08014","title":"Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking","created":"2025-07-06","cited_by_count":0,"area":"safety"},{"id":"2606.21082","title":"Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversations","created":"2026-06-19","cited_by_count":0,"area":"safety"},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"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":"2610.06064","title":"TrustMI: Causally controlling how assistants trust their users","created":"2026-10-05","cited_by_count":0,"area":"safety"}],"next_cursor":null}