{"total":96,"rows":[{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2405.13401","title":"TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models","created":"2024-05-22","cited_by_count":67,"area":"rag"},{"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":"2408.10848","title":"Perception-guided Jailbreak against Text-to-Image Models","created":"2024-08-20","cited_by_count":40,"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":"2502.12575","title":"DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent","created":"2025-02-18","cited_by_count":23,"area":"agents"},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21,"area":"safety"},{"id":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2501.17858","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","created":"2025-01-29","cited_by_count":17,"area":null},{"id":"2502.13141","title":"UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models","created":"2025-02-18","cited_by_count":16,"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":"2502.02958","title":"Position: Editing Large Language Models Poses Serious Safety Risks","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2505.12567","title":"A Survey of Attacks on Large Language Models","created":"2025-05-18","cited_by_count":15,"area":"agents"},{"id":"2405.02765","title":"Has this Fact been Edited? Detecting Knowledge Edits in Language Models","created":"2024-05-04","cited_by_count":14,"area":null},{"id":"2411.15432","title":"Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts","created":"2024-11-23","cited_by_count":14,"area":"mllm"},{"id":"2504.18598","title":"BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts","created":"2025-04-24","cited_by_count":14,"area":"moe"},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2408.09878","title":"Transferring Backdoors between Large Language Models by Knowledge Distillation","created":"2024-08-19","cited_by_count":12,"area":"safety"},{"id":"2502.18511","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","created":"2025-02-22","cited_by_count":11,"area":"safety"},{"id":"2405.20770","title":"Large Language Model Sentinel: LLM Agent for Adversarial Purification","created":"2024-05-24","cited_by_count":10,"area":"agents"},{"id":"2504.13562","title":"DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification","created":"2025-04-18","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":"2409.00399","title":"Rethinking Backdoor Detection Evaluation for Language Models","created":"2024-08-31","cited_by_count":9,"area":"lr"},{"id":"2410.12586","title":"How to Make LLMs Forget: On Reversing In-Context Knowledge Edits","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2412.02454","title":"Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining","created":"2024-12-03","cited_by_count":9,"area":"safety"},{"id":"2507.01321","title":"ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks","created":"2025-07-02","cited_by_count":9,"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":"2412.13341","title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2506.06518","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2409.19663","title":"Identifying Knowledge Editing Types in Large Language Models","created":"2024-09-29","cited_by_count":7,"area":null},{"id":"2410.08604","title":"MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2505.20819","title":"Tracing and Reversing Edits in LLMs","created":"2025-05-27","cited_by_count":7,"area":null},{"id":"2512.14741","title":"Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs","created":"2025-12-12","cited_by_count":7,"area":"safety"},{"id":"2504.11182","title":"Exploring Backdoor Attack and Defense for LLM-empowered Recommendations","created":"2025-04-15","cited_by_count":6,"area":"safety"},{"id":"2507.05288","title":"A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models","created":"2025-07-05","cited_by_count":6,"area":null},{"id":"2510.10265","title":"Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models","created":"2025-10-11","cited_by_count":6,"area":"safety"},{"id":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"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":"2505.15674","title":"UniErase: Towards Balanced and Precise Unlearning in Language Models","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2601.23081","title":"Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures","created":"2026-01-30","cited_by_count":5,"area":"safety"},{"id":"2408.10411","title":"Resolving Lexical Bias in Model Editing","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2510.16367","title":"EditMark: Watermarking Large Language Models based on Model Editing","created":"2025-10-18","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":"2604.12359","title":"Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"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":"2406.12670","title":"Stealth edits to large language models","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2409.05806","title":"CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2410.18267","title":"Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2503.01896","title":"Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2505.23001","title":"DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors","created":"2025-05-29","cited_by_count":3,"area":"safety"},{"id":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2511.20892","title":"Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2512.19297","title":"Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.07466","title":"Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2411.07691","title":"New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2503.12899","title":"A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2505.03501","title":"BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models","created":"2025-05-06","cited_by_count":2,"area":"safety"},{"id":"2505.15175","title":"A Linear Approach to Data Poisoning","created":"2025-05-21","cited_by_count":2,"area":"safety"},{"id":"2511.05852","title":"Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2602.22246","title":"Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models","created":"2026-02-24","cited_by_count":2,"area":"diffusion"},{"id":"2406.19753","title":"Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning","created":"2024-06-28","cited_by_count":1,"area":"safety"},{"id":"2407.20281","title":"NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2504.17070","title":"MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2506.01825","title":"Backdoors in Code Summarizers: How Bad Is It?","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2506.13285","title":"DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.19775","title":"bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2604.21700","title":"Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers","created":"2026-04-23","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":"2605.15172","title":"MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs","created":"2026-05-14","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":"2508.02312","title":"Data Security in Large Language Models: Risks, Defense, and Directions","created":"2025-08-04","cited_by_count":0,"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":"2509.16268","title":"Digging Into the Internal: Causality-Based Analysis of LLM Function Calling","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2510.10486","title":"MEASER: Malware embedding attacks on open-source LLMs","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2602.04898","title":"Semantic-level Backdoor Attack against Text-to-Image Diffusion Models","created":"2026-02-03","cited_by_count":0,"area":"diffusion"},{"id":"2602.06887","title":"Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations","created":"2026-02-06","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":"2604.24162","title":"Defusing the Trigger: Tail-Risk-Informed Attention Rebalancing for LLM Backdoor Mitigation","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2604.27426","title":"Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors","created":"2026-04-30","cited_by_count":0,"area":"safety"},{"id":"2606.07963","title":"Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs","created":"2026-06-06","cited_by_count":0,"area":"safety"},{"id":"2606.27511","title":"When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems","created":"2026-06-25","cited_by_count":0,"area":"safety"},{"id":"2607.17550","title":"(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure","created":"2026-07-20","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":"2607.25227","title":"Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.11295","title":"Backdoor Decontamination Dynamics in LLM Agents","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.17836","title":"Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.01023","title":"AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2609.06612","title":"MechAudit-40: White-Box Auditing across 40 LLM Attack Mechanisms","created":"2026-09-06","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"}],"next_cursor":null}