{"total":66,"rows":[{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333,"area":"safety"},{"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":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259,"area":"safety"},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244,"area":"safety"},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223,"area":"safety"},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216,"area":"safety"},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215,"area":"safety"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157,"area":"safety"},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139,"area":"safety"},{"id":"2405.20773","title":"Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character","created":"2024-05-25","cited_by_count":68,"area":"safety"},{"id":"2311.08592","title":"AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications","created":"2023-11-14","cited_by_count":54,"area":"safety"},{"id":"2502.16580","title":"Can Indirect Prompt Injection Attacks Be Detected and Removed?","created":"2025-02-23","cited_by_count":52,"area":"safety"},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2411.00459","title":"Defense Against Prompt Injection Attack by Leveraging Attack Techniques","created":"2024-11-01","cited_by_count":40,"area":"safety"},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2402.15302","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","created":"2024-02-23","cited_by_count":27,"area":"safety"},{"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":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"area":"safety"},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"area":"safety"},{"id":"2311.09763","title":"Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations","created":"2023-11-16","cited_by_count":21,"area":"safety"},{"id":"2406.05344","title":"MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention","created":"2024-06-08","cited_by_count":20,"area":"safety"},{"id":"2310.00833","title":"Necessary and Sufficient Watermark for Large Language Models","created":"2023-10-02","cited_by_count":19,"area":"safety"},{"id":"2407.00869","title":"Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks","created":"2024-07-01","cited_by_count":19,"area":"safety"},{"id":"2507.13686","title":"TopicAttack: An Indirect Prompt Injection Attack via Topic Transition","created":"2025-07-18","cited_by_count":17,"area":"safety"},{"id":"2504.20472","title":"Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction","created":"2025-04-29","cited_by_count":16,"area":"safety"},{"id":"2509.26238","title":"Beyond Linear Probes: Dynamic Safety Monitoring for Language Models","created":"2025-09-30","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":"2310.18603","title":"Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers","created":"2023-10-28","cited_by_count":14,"area":"safety"},{"id":"2411.14133","title":"GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs","created":"2024-11-21","cited_by_count":12,"area":"safety"},{"id":"2306.08833","title":"Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection","created":"2023-06-15","cited_by_count":11,"area":"safety"},{"id":"2403.08701","title":"Review of Generative AI Methods in Cybersecurity","created":"2024-03-13","cited_by_count":9,"area":"safety"},{"id":"2505.17650","title":"Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?","created":"2025-05-23","cited_by_count":9,"area":"safety"},{"id":"2404.18534","title":"Evaluating and Mitigating Linguistic Discrimination in Large Language Models","created":"2024-04-29","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":"2407.04151","title":"Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers","created":"2024-07-04","cited_by_count":5,"area":"safety"},{"id":"2604.15022","title":"Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization","created":"2026-04-16","cited_by_count":5,"area":"safety"},{"id":"2405.11466","title":"Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code","created":"2024-05-19","cited_by_count":4,"area":"safety"},{"id":"2407.00075","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference","created":"2024-06-21","cited_by_count":4,"area":"safety"},{"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":"2604.06840","title":"MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning","created":"2026-04-08","cited_by_count":4,"area":"safety"},{"id":"2310.11079","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models","created":"2023-10-17","cited_by_count":3,"area":"safety"},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2510.03705","title":"Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods","created":"2025-10-04","cited_by_count":3,"area":"safety"},{"id":"2602.13547","title":"AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks","created":"2026-02-14","cited_by_count":3,"area":"safety"},{"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":"2604.09235","title":"Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor","created":"2026-04-10","cited_by_count":2,"area":"safety"},{"id":"2402.12936","title":"Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERT","created":"2024-02-20","cited_by_count":1,"area":"safety"},{"id":"2504.06577","title":"Bypassing Safety Guardrails in LLMs Using Humor","created":"2025-04-09","cited_by_count":1,"area":"safety"},{"id":"2505.00010","title":"Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models","created":"2025-04-21","cited_by_count":1,"area":"safety"},{"id":"2506.13494","title":"Watermarking LLM-Generated Datasets in Downstream Tasks","created":"2025-06-16","cited_by_count":1,"area":"safety"},{"id":"2508.06153","title":"SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs","created":"2025-08-08","cited_by_count":1,"area":"safety"},{"id":"2509.07768","title":"Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning","created":"2025-09-09","cited_by_count":1,"area":"safety"},{"id":"2510.15976","title":"Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization","created":"2025-10-13","cited_by_count":1,"area":"safety"},{"id":"2510.17000","title":"Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs","created":"2025-10-19","cited_by_count":1,"area":"safety"},{"id":"2606.25057","title":"LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges","created":"2026-06-23","cited_by_count":1,"area":"safety"},{"id":"2411.16730","title":"\"Moralized\" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks","created":"2024-11-23","cited_by_count":0,"area":"safety"},{"id":"2511.05532","title":"Beyond One-Size-Fits-All: Personalized Harmful Content Detection with In-Context Learning","created":"2025-10-29","cited_by_count":0,"area":"safety"},{"id":"2605.02940","title":"PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.17610","title":"SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening","created":"2026-05-17","cited_by_count":0,"area":"safety"},{"id":"2606.24267","title":"Pigeonholing: how bad prompts hurt models, causing collapse and mistakes","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.03932","title":"MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs","created":"2026-07-04","cited_by_count":0,"area":"safety"},{"id":"2608.12623","title":"When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers","created":"2026-08-12","cited_by_count":0,"area":"safety"},{"id":"2609.04495","title":"Rethinking Indirect Prompt Injection as a Test-Time Search Problem","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2610.08840","title":"Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}