{"total":110,"rows":[{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"area":"safety"},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223,"area":"safety"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"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":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"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":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2604.09378","title":"BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning","created":"2026-04-10","cited_by_count":27,"area":"safety"},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2407.04108","title":"Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs","created":"2024-07-04","cited_by_count":15,"area":"safety"},{"id":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"id":"2602.03085","title":"The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers","created":"2026-02-03","cited_by_count":14,"area":"safety"},{"id":"2409.01193","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","created":"2024-09-02","cited_by_count":13,"area":"safety"},{"id":"2405.07667","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","created":"2024-05-13","cited_by_count":12,"area":"safety"},{"id":"2506.14003","title":"Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs","created":"2025-06-16","cited_by_count":11,"area":"safety"},{"id":"2411.19876","title":"LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states","created":"2024-11-29","cited_by_count":10,"area":"safety"},{"id":"2505.17601","title":"Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs","created":"2025-05-23","cited_by_count":10,"area":"safety"},{"id":"2509.21761","title":"Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models","created":"2025-09-26","cited_by_count":10,"area":"safety"},{"id":"2408.10722","title":"MEGen: Generative Backdoor into Large Language Models via Model Editing","created":"2024-08-20","cited_by_count":8,"area":"safety"},{"id":"2403.09603","title":"Optimistic Verifiable Training by Controlling Hardware Nondeterminism","created":"2024-03-14","cited_by_count":7,"area":"safety"},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2512.14741","title":"Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs","created":"2025-12-12","cited_by_count":7,"area":"safety"},{"id":"2601.22136","title":"StepShield: When, Not Whether to Intervene on Rogue Agents","created":"2026-01-29","cited_by_count":7,"area":"safety"},{"id":"2603.13461","title":"Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference","created":"2026-03-13","cited_by_count":7,"area":"safety"},{"id":"2410.13691","title":"Jailbreaking LLM-Controlled Robots","created":"2024-10-17","cited_by_count":6,"area":"safety"},{"id":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2505.07610","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","created":"2025-05-12","cited_by_count":6,"area":"safety"},{"id":"2510.17021","title":"Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning","created":"2025-10-19","cited_by_count":6,"area":"safety"},{"id":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"safety"},{"id":"2502.16423","title":"Unified Prompt Attack Against Text-to-Image Generation Models","created":"2025-02-23","cited_by_count":5,"area":"safety"},{"id":"2505.20435","title":"The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology","created":"2025-05-26","cited_by_count":5,"area":"safety"},{"id":"2505.12871","title":"Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?","created":"2025-05-19","cited_by_count":4,"area":"safety"},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2406.05660","title":"Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models","created":"2024-06-09","cited_by_count":3,"area":"safety"},{"id":"2508.15847","title":"Mechanistic Exploration of Backdoored Large Language Model Attention Patterns","created":"2025-08-19","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":"2510.15106","title":"PoTS: Proof-of-Training-Steps for Backdoor Detection in Large Language Models","created":"2025-10-16","cited_by_count":3,"area":"safety"},{"id":"2602.00298","title":"Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning","created":"2026-01-30","cited_by_count":3,"area":"safety"},{"id":"2505.15175","title":"A Linear Approach to Data Poisoning","created":"2025-05-21","cited_by_count":2,"area":"safety"},{"id":"2508.16325","title":"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2510.05169","title":"From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs","created":"2025-10-05","cited_by_count":2,"area":"safety"},{"id":"2602.10382","title":"Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"safety"},{"id":"2602.18782","title":"MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs","created":"2026-02-21","cited_by_count":2,"area":"safety"},{"id":"2604.06436","title":"The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?","created":"2026-04-07","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":"2605.18646","title":"Language-Switching Triggers Take a Latent Detour Through Language Models","created":"2026-05-18","cited_by_count":2,"area":"safety"},{"id":"2606.08044","title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","created":"2026-06-06","cited_by_count":2,"area":"safety"},{"id":"2606.19535","title":"FloatDoor: Platform-Triggered Backdoors in LLMs","created":"2026-06-17","cited_by_count":2,"area":"safety"},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2510.04528","title":"Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers","created":"2025-10-06","cited_by_count":1,"area":"safety"},{"id":"2602.00822","title":"Safety-Efficacy Trade Off: Robustness against Data-Poisoning","created":"2026-01-31","cited_by_count":1,"area":"safety"},{"id":"2602.13427","title":"Backdooring Bias in Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"safety"},{"id":"2603.29038","title":"Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning","created":"2026-03-30","cited_by_count":1,"area":"safety"},{"id":"2604.18970","title":"Mechanistic Anomaly Detection via Functional Attribution","created":"2026-04-21","cited_by_count":1,"area":"safety"},{"id":"2605.06846","title":"Narrow Secret Loyalty Dodges Black-Box Audits","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2605.12529","title":"BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models","created":"2026-04-15","cited_by_count":1,"area":"safety"},{"id":"2605.20641","title":"Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs","created":"2026-05-20","cited_by_count":1,"area":"safety"},{"id":"2605.25073","title":"Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions","created":"2026-05-24","cited_by_count":1,"area":"safety"},{"id":"2605.30189","title":"Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection","created":"2026-05-28","cited_by_count":1,"area":"safety"},{"id":"2606.09890","title":"PreAct-Bench: Benchmarking Predictive Monitoring in LLMs","created":"2026-06-03","cited_by_count":1,"area":"safety"},{"id":"2606.23700","title":"Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2607.26849","title":"ToxScreen: Detecting Whether an LLM Has Been Poisoned","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2610.04985","title":"Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use","created":"2026-10-04","cited_by_count":1,"area":"safety"},{"id":"2509.05318","title":"Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models","created":"2025-08-30","cited_by_count":0,"area":"safety"},{"id":"2512.04841","title":"SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security","created":"2025-12-04","cited_by_count":0,"area":"safety"},{"id":"2602.12124","title":"Alignment Risks from Capability-Seeking RL Training","created":"2026-02-12","cited_by_count":0,"area":"safety"},{"id":"2603.15692","title":"BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator","created":"2026-03-16","cited_by_count":0,"area":"safety"},{"id":"2603.17174","title":"Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2603.20976","title":"Detection of adversarial intent in Human-AI teams using LLMs","created":"2026-03-21","cited_by_count":0,"area":"safety"},{"id":"2604.10403","title":"Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs","created":"2026-04-12","cited_by_count":0,"area":"safety"},{"id":"2605.11612","title":"When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.13471","title":"Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2605.19147","title":"Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks","created":"2026-05-18","cited_by_count":0,"area":"safety"},{"id":"2606.08892","title":"Diffuse AI Control on Fuzzy Tasks","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2606.29646","title":"Fuzzing Large Language Models to Elicit Hidden Behaviours","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2606.30899","title":"Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2607.19894","title":"Defense Against LLM Backdoors using Critical Neuron Isolation Pruning","created":"2026-07-22","cited_by_count":0,"area":"safety"},{"id":"2608.06795","title":"LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes","created":"2026-08-07","cited_by_count":0,"area":"safety"},{"id":"2608.08212","title":"Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment","created":"2026-08-08","cited_by_count":0,"area":"safety"},{"id":"2608.27512","title":"Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2608.30362","title":"Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.01023","title":"AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2609.07746","title":"LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders","created":"2026-09-07","cited_by_count":0,"area":"safety"},{"id":"2609.13478","title":"BadEngram: Backdoor Attack on Gated Memory Components in LLMs","created":"2026-09-11","cited_by_count":0,"area":"safety"},{"id":"2609.21996","title":"A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.24826","title":"OPBackdoor: Opportunistic Backdoors via Alibi-Aligned Reasoning","created":"2026-09-21","cited_by_count":0,"area":"safety"},{"id":"2609.26131","title":"StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots","created":"2026-08-07","cited_by_count":0,"area":"safety"},{"id":"2609.30217","title":"Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure","created":"2026-09-24","cited_by_count":0,"area":"safety"},{"id":"2609.32288","title":"A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents","created":"2026-09-26","cited_by_count":0,"area":"safety"},{"id":"2609.35356","title":"Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits","created":"2026-09-28","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}