{"total":68,"rows":[{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493,"area":"safety"},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375,"area":"safety"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"area":"safety"},{"id":"2409.11295","title":"EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage","created":"2024-09-17","cited_by_count":150,"area":"agents"},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2312.17673","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","created":"2023-12-29","cited_by_count":106,"area":"safety"},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89,"area":"safety"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2408.01605","title":"CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models","created":"2024-08-02","cited_by_count":58,"area":null},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"area":null},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"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":"2506.01055","title":"Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution","created":"2025-06-01","cited_by_count":26,"area":"agents"},{"id":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","cited_by_count":25,"area":"safety"},{"id":"2602.11510","title":"AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems","created":"2026-02-12","cited_by_count":25,"area":"agents"},{"id":"2404.06921","title":"GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications","created":"2024-04-10","cited_by_count":23,"area":null},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"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,"area":"safety"},{"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":"2311.07884","title":"Fair Abstractive Summarization of Diverse Perspectives","created":"2023-11-14","cited_by_count":17,"area":null},{"id":"2603.12277","title":"Prompt Injection as Role Confusion","created":"2026-02-22","cited_by_count":17,"area":"safety"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2507.13169","title":"Prompt Injection 2.0: Hybrid AI Threats","created":"2025-07-17","cited_by_count":13,"area":"safety"},{"id":"2603.11853","title":"OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents","created":"2026-03-12","cited_by_count":11,"area":"agents"},{"id":"2503.06269","title":"Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models","created":"2025-03-08","cited_by_count":10,"area":"mechinterp"},{"id":"2410.09097","title":"Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations","created":"2024-10-09","cited_by_count":8,"area":"safety"},{"id":"2607.26115","title":"GPT-Red: Automated Red Teaming via Self-Play at Scale","created":"2026-07-28","cited_by_count":8,"area":"synth"},{"id":"2407.02987","title":"LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models","created":"2024-07-03","cited_by_count":7,"area":"alignment"},{"id":"2410.13901","title":"SoK: Prompt Hacking of Large Language Models","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2410.15641","title":"SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis","created":"2024-10-21","cited_by_count":7,"area":"safety"},{"id":"2507.19598","title":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","created":"2025-07-25","cited_by_count":7,"area":null},{"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":"2412.02159","title":"Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach","created":"2024-12-03","cited_by_count":6,"area":"safety"},{"id":"2505.00626","title":"The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)","created":"2025-05-01","cited_by_count":6,"area":null},{"id":"2408.01725","title":"The Drama Machine: Simulating Character Development with LLM Agents","created":"2024-08-03","cited_by_count":5,"area":"agents"},{"id":"2604.16966","title":"Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning","created":"2026-04-18","cited_by_count":5,"area":"agents"},{"id":"2504.19855","title":"The Automation Advantage in AI Red Teaming","created":"2025-04-28","cited_by_count":4,"area":"safety"},{"id":"2605.00583","title":"Jailbreaking Vision-Language Models Through the Visual Modality","created":"2026-05-01","cited_by_count":4,"area":"mllm"},{"id":"2401.01537","title":"The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers","created":"2024-01-03","cited_by_count":3,"area":null},{"id":"2412.16359","title":"Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context","created":"2024-12-20","cited_by_count":3,"area":"safety"},{"id":"2502.12630","title":"Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach","created":"2025-02-18","cited_by_count":3,"area":"agents"},{"id":"2510.00451","title":"A Call to Action for a Secure-by-Design Generative AI Paradigm","created":"2025-10-01","cited_by_count":3,"area":"safety"},{"id":"2510.00452","title":"Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensics","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2601.14298","title":"Guardrails for trust, safety, and ethical development and deployment of Large Language Models (LLM)","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2402.06922","title":"Whispers in the Machine: Confidentiality in Agentic Systems","created":"2024-02-10","cited_by_count":2,"area":"agents"},{"id":"2504.09712","title":"The Structural Safety Generalization Problem","created":"2025-04-13","cited_by_count":2,"area":"safety"},{"id":"2507.02699","title":"Your Mailbox Is Mine: Prompt Injection Attacks Against Real-World LLM Email Agents","created":"2025-07-03","cited_by_count":2,"area":"agents"},{"id":"2602.10179","title":"When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models","created":"2026-02-10","cited_by_count":2,"area":"safety"},{"id":"2604.16838","title":"enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways","created":"2026-04-18","cited_by_count":2,"area":null},{"id":"2604.03912","title":"Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework","created":"2026-04-05","cited_by_count":1,"area":"safety"},{"id":"2605.20351","title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2403.00292","title":"Enhancing Jailbreak Attacks with Diversity Guidance","created":"2024-03-01","cited_by_count":0,"area":"safety"},{"id":"2404.08309","title":"Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts","created":"2024-04-12","cited_by_count":0,"area":"safety"},{"id":"2406.11880","title":"Knowledge Return Oriented Prompting (KROP)","created":"2024-06-11","cited_by_count":0,"area":"safety"},{"id":"2506.08885","title":"AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2509.04615","title":"Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs","created":"2025-09-04","cited_by_count":0,"area":"alignment"},{"id":"2601.00867","title":"The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models","created":"2025-12-30","cited_by_count":0,"area":"safety"},{"id":"2603.07286","title":"Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.17123","title":"Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.23887","title":"Evaluation of Prompt Injection Defenses in Large Language Models","created":"2026-04-26","cited_by_count":0,"area":"safety"},{"id":"2607.17786","title":"Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.11082","title":"ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.20188","title":"ResumeShield: Channel Separation and an Open Benchmark for Indirect Prompt Injection in AI Resume Screening","created":"2026-07-24","cited_by_count":0,"area":"safety"}],"next_cursor":null}