{"list":"other","total":73,"rows":[{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2403.02691","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","created":"2024-03-05","cited_by_count":538},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278},{"id":"2403.14720","title":"Defending Against Indirect Prompt Injection Attacks With Spotlighting","created":"2024-03-20","cited_by_count":267},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216},{"id":"2305.12082","title":"SneakyPrompt: Jailbreaking Text-to-image Generative Models","created":"2023-05-20","cited_by_count":189},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145},{"id":"2307.00691","title":"From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy","created":"2023-07-03","cited_by_count":143},{"id":"2403.17710","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","created":"2024-03-26","cited_by_count":143},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136},{"id":"2403.09513","title":"AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting","created":"2024-03-14","cited_by_count":125},{"id":"2311.11855","title":"Evil Geniuses: Delving into the Safety of LLM-based Agents","created":"2023-11-20","cited_by_count":106},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87},{"id":"2403.03792","title":"Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks","created":"2024-03-06","cited_by_count":85},{"id":"2402.10753","title":"ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages","created":"2024-02-16","cited_by_count":82},{"id":"2401.11880","title":"PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety","created":"2024-01-22","cited_by_count":80},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79},{"id":"2405.05610","title":"Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM","created":"2024-05-09","cited_by_count":77},{"id":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76},{"id":"2407.17436","title":"AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies","created":"2024-07-11","cited_by_count":74},{"id":"2404.02928","title":"Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models","created":"2024-04-02","cited_by_count":72},{"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},{"id":"2305.14950","title":"Adversarial Demonstration Attacks on Large Language Models","created":"2023-05-24","cited_by_count":63},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50},{"id":"2406.11036","title":"garak: A Framework for Security Probing Large Language Models","created":"2024-06-16","cited_by_count":49},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49},{"id":"2407.16667","title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","created":"2024-07-23","cited_by_count":44},{"id":"2407.15050","title":"Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts","created":"2024-07-21","cited_by_count":42},{"id":"2402.11755","title":"SPML: A DSL for Defending Language Models Against Prompt Attacks","created":"2024-02-19","cited_by_count":34},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32},{"id":"2410.02828","title":"PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System","created":"2024-10-01","cited_by_count":31},{"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},{"id":"2309.11830","title":"Goal-Oriented Prompt Attack and Safety Evaluation for LLMs","created":"2023-09-21","cited_by_count":24},{"id":"2404.07234","title":"Goal-guided Generative Prompt Injection Attack on Large Language Models","created":"2024-04-06","cited_by_count":24},{"id":"2404.16030","title":"MoDE: CLIP Data Experts via Clustering","created":"2024-04-24","cited_by_count":22},{"id":"2311.06237","title":"Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming","created":"2023-11-10","cited_by_count":21},{"id":"2406.07954","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","created":"2024-06-12","cited_by_count":20},{"id":"2404.05264","title":"Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security","created":"2024-04-08","cited_by_count":19},{"id":"2405.20902","title":"Preemptive Answer \"Attacks\" on Chain-of-Thought Reasoning","created":"2024-05-31","cited_by_count":19},{"id":"2408.05025","title":"Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks","created":"2024-08-09","cited_by_count":17},{"id":"2312.10982","title":"A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models","created":"2023-12-18","cited_by_count":14},{"id":"2407.03876","title":"Automated Progressive Red Teaming","created":"2024-07-04","cited_by_count":13},{"id":"2312.06924","title":"Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack","created":"2023-12-12","cited_by_count":11},{"id":"2410.03869","title":"Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step","created":"2024-10-04","cited_by_count":11},{"id":"2407.16318","title":"PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing","created":"2024-07-23","cited_by_count":10},{"id":"2507.01513","title":"SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism","created":"2025-07-02","cited_by_count":10},{"id":"2404.17098","title":"CLARE: Cognitive Load Assessment in REaltime with Multimodal Data","created":"2024-04-26","cited_by_count":8},{"id":"2407.15399","title":"Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models","created":"2024-07-22","cited_by_count":7},{"id":"2409.13331","title":"Applying Pre-trained Multilingual BERT in Embeddings for Improved Malicious Prompt Injection Attacks Detection","created":"2024-09-20","cited_by_count":7},{"id":"2410.13901","title":"SoK: Prompt Hacking of Large Language Models","created":"2024-10-16","cited_by_count":7},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7},{"id":"2210.06163","title":"Privacy of federated QR decomposition using additive secure multiparty computation","created":"2022-10-12","cited_by_count":1},{"id":"2406.02577","title":"Are PPO-ed Language Models Hackable?","created":"2024-05-28","cited_by_count":1}],"next_cursor":null}