{"total":93,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2501.09004","title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","created":"2025-01-15","cited_by_count":132,"area":"safety"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68,"area":"safety"},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"area":"safety"},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54,"area":"safety"},{"id":"2406.11036","title":"garak: A Framework for Security Probing Large Language Models","created":"2024-06-16","cited_by_count":49,"area":"safety"},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","cited_by_count":46,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2412.06878","title":"SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations","created":"2024-12-09","cited_by_count":38,"area":"safety"},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2409.14729","title":"PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs","created":"2024-09-23","cited_by_count":17,"area":"safety"},{"id":"2409.15398","title":"Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI","created":"2024-09-23","cited_by_count":16,"area":"safety"},{"id":"2404.04392","title":"Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes","created":"2024-04-05","cited_by_count":14,"area":"safety"},{"id":"2410.22153","title":"Benchmarking LLM Guardrails in Handling Multilingual Toxicity","created":"2024-10-29","cited_by_count":14,"area":"safety"},{"id":"2410.21083","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","created":"2024-10-28","cited_by_count":12,"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":"2504.18564","title":"DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization","created":"2025-04-21","cited_by_count":12,"area":"safety"},{"id":"2410.16527","title":"Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis","created":"2024-10-21","cited_by_count":10,"area":"safety"},{"id":"2502.15427","title":"Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs","created":"2025-02-21","cited_by_count":9,"area":"safety"},{"id":"2601.09625","title":"The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism","created":"2026-01-14","cited_by_count":9,"area":"safety"},{"id":"2408.08959","title":"Trust-Oriented Adaptive Guardrails for Large Language Models","created":"2024-08-16","cited_by_count":8,"area":"safety"},{"id":"2411.14398","title":"Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings","created":"2024-11-21","cited_by_count":8,"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":"2409.17190","title":"Enhancing Guardrails for Safe and Secure Healthcare AI","created":"2024-09-25","cited_by_count":7,"area":"safety"},{"id":"2507.21820","title":"Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is","created":"2025-07-29","cited_by_count":7,"area":"safety"},{"id":"2410.02916","title":"LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks","created":"2024-10-03","cited_by_count":6,"area":"safety"},{"id":"2503.11127","title":"Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning","created":"2025-03-14","cited_by_count":6,"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":"2504.18333","title":"Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections","created":"2025-04-25","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":"2406.10847","title":"TorchOpera: A Compound AI System for LLM Safety","created":"2024-06-16","cited_by_count":4,"area":"safety"},{"id":"2607.22868","title":"What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents","created":"2026-07-24","cited_by_count":4,"area":"safety"},{"id":"2411.12946","title":"A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection","created":"2024-11-20","cited_by_count":3,"area":"safety"},{"id":"2504.19333","title":"Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing","created":"2025-04-27","cited_by_count":3,"area":"safety"},{"id":"2507.21170","title":"OneShield -- the Next Generation of LLM Guardrails","created":"2025-07-25","cited_by_count":3,"area":"safety"},{"id":"2510.05310","title":"RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts","created":"2025-10-06","cited_by_count":3,"area":"safety"},{"id":"2512.24044","title":"Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?","created":"2025-12-30","cited_by_count":3,"area":"safety"},{"id":"2601.19726","title":"RvB: Automating AI System Hardening via Iterative Red-Blue Games","created":"2026-01-27","cited_by_count":3,"area":"safety"},{"id":"2502.11006","title":"Prompt Inject Detection with Generative Explanation as an Investigative Tool","created":"2025-02-16","cited_by_count":2,"area":"safety"},{"id":"2504.09712","title":"The Structural Safety Generalization Problem","created":"2025-04-13","cited_by_count":2,"area":"safety"},{"id":"2505.14524","title":"Guarded Query Routing for Large Language Models","created":"2025-05-20","cited_by_count":2,"area":"safety"},{"id":"2512.19011","title":"Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale","created":"2025-12-22","cited_by_count":2,"area":"safety"},{"id":"2601.19051","title":"Proactive Hardening of LLM Defenses with HASTE","created":"2026-01-27","cited_by_count":2,"area":"safety"},{"id":"2603.02588","title":"ExpGuard: LLM Content Moderation in Specialized Domains","created":"2026-03-03","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":"2402.03303","title":"Nevermind: Instruction Override and Moderation in Large Language Models","created":"2024-02-05","cited_by_count":1,"area":"safety"},{"id":"2407.06323","title":"When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails","created":"2024-07-08","cited_by_count":1,"area":"safety"},{"id":"2506.19109","title":"Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection Systems","created":"2025-06-23","cited_by_count":1,"area":"safety"},{"id":"2509.16870","title":"DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems","created":"2025-09-21","cited_by_count":1,"area":"safety"},{"id":"2510.13727","title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","created":"2025-10-15","cited_by_count":1,"area":"safety"},{"id":"2510.26847","title":"Broken-Token: Filtering Obfuscated Prompts by Counting Characters-Per-Token","created":"2025-10-30","cited_by_count":1,"area":"safety"},{"id":"2601.17481","title":"Lattice: Generative Guardrails for Conversational Agents","created":"2026-01-24","cited_by_count":1,"area":"safety"},{"id":"2602.02509","title":"CodeGuard: Improving LLM Guardrails in CS Education","created":"2026-01-22","cited_by_count":1,"area":"safety"},{"id":"2602.02595","title":"To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack","created":"2026-02-01","cited_by_count":1,"area":"safety"},{"id":"2602.10481","title":"Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI","created":"2026-02-11","cited_by_count":1,"area":"safety"},{"id":"2602.15853","title":"A Lightweight Explainable Guardrail for Prompt Safety","created":"2026-01-24","cited_by_count":1,"area":"safety"},{"id":"2602.18583","title":"Luna-2: Scalable Single-Token Evaluation with Small Language Models","created":"2026-02-20","cited_by_count":1,"area":"safety"},{"id":"2603.12023","title":"Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems","created":"2026-03-12","cited_by_count":1,"area":"safety"},{"id":"2603.18433","title":"Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems","created":"2026-03-19","cited_by_count":1,"area":"safety"},{"id":"2604.01444","title":"Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models","created":"2026-04-01","cited_by_count":1,"area":"safety"},{"id":"2604.16542","title":"TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts","created":"2026-04-17","cited_by_count":1,"area":"safety"},{"id":"2605.30693","title":"Triaging Threats to Specialized Guardrails","created":"2026-05-29","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":"2606.19242","title":"Runtime Compliance Verification for AI Agents","created":"2026-06-17","cited_by_count":1,"area":"safety"},{"id":"2606.27210","title":"Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes","created":"2026-06-25","cited_by_count":1,"area":"safety"},{"id":"2607.01277","title":"Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety","created":"2026-07-01","cited_by_count":1,"area":"safety"},{"id":"2407.13744","title":"LLMs as Function Approximators: Terminology, Taxonomy, and Questions for Evaluation","created":"2024-07-18","cited_by_count":0,"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":"2502.09175","title":"FLAME: Flexible LLM-Assisted Moderation Engine","created":"2025-02-13","cited_by_count":0,"area":"safety"},{"id":"2503.00600","title":"Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems","created":"2025-03-01","cited_by_count":0,"area":"safety"},{"id":"2508.18384","title":"Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails","created":"2025-08-25","cited_by_count":0,"area":"safety"},{"id":"2511.23174","title":"Are LLMs Good Safety Agents or a Propaganda Engine?","created":"2025-11-28","cited_by_count":0,"area":"safety"},{"id":"2602.15391","title":"Improving LLM Reliability through Hybrid Abstention and Adaptive Detection","created":"2026-02-17","cited_by_count":0,"area":"safety"},{"id":"2603.16192","title":"Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.23067","title":"Training a General Purpose Automated Red Teaming Model","created":"2026-04-24","cited_by_count":0,"area":"safety"},{"id":"2605.06669","title":"Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs","created":"2026-03-29","cited_by_count":0,"area":"safety"},{"id":"2605.10901","title":"Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","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":"2607.18268","title":"Fence: Specialized SLM Guardrails for LLM Applications","created":"2026-05-22","cited_by_count":0,"area":"safety"},{"id":"2607.19366","title":"Geometry-Guided Constraint Learning for LLM Safety Classification","created":"2026-06-09","cited_by_count":0,"area":"safety"},{"id":"2607.22926","title":"SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI","created":"2026-07-24","cited_by_count":0,"area":"safety"},{"id":"2608.10279","title":"Withholding the Completing Chunk: Exact Release-Boundary Equivalence for Production Streaming Guardrails","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2608.26306","title":"Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systems","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2608.28646","title":"BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice","created":"2026-08-14","cited_by_count":0,"area":"safety"},{"id":"2609.00790","title":"RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2609.10707","title":"Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation","created":"2026-09-09","cited_by_count":0,"area":"safety"},{"id":"2609.21484","title":"HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.33671","title":"COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints","created":"2026-09-27","cited_by_count":0,"area":"safety"}],"next_cursor":null}