{"total":211,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489,"area":"safety"},{"id":"2406.03007","title":"BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents","created":"2024-06-05","cited_by_count":115,"area":"agents"},{"id":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96,"area":"safety"},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95,"area":"safety"},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2305.04175","title":"Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning","created":"2023-05-07","cited_by_count":92,"area":"diffusion"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74,"area":"safety"},{"id":"2310.07676","title":"Composite Backdoor Attacks Against Large Language Models","created":"2023-10-11","cited_by_count":73,"area":"safety"},{"id":"2209.06015","title":"Black-box Dataset Ownership Verification via Backdoor Watermarking","created":"2022-08-04","cited_by_count":65,"area":null},{"id":"2209.11715","title":"The \"Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices","created":"2022-09-23","cited_by_count":63,"area":null},{"id":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63,"area":"safety"},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62,"area":"safety"},{"id":"2211.02408","title":"Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis","created":"2022-11-04","cited_by_count":59,"area":"safety"},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55,"area":null},{"id":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51,"area":null},{"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":"2101.06969","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","created":"2021-01-18","cited_by_count":49,"area":null},{"id":"2301.02496","title":"Stealthy Backdoor Attack for Code Models","created":"2023-01-06","cited_by_count":49,"area":"safety"},{"id":"2202.05749","title":"Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense","created":"2022-02-11","cited_by_count":47,"area":"safety"},{"id":"2304.02786","title":"UNICORN: A Unified Backdoor Trigger Inversion Framework","created":"2023-04-05","cited_by_count":46,"area":null},{"id":"2201.11692","title":"SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders","created":"2022-01-27","cited_by_count":45,"area":null},{"id":"2210.13865","title":"Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation","created":"2022-10-25","cited_by_count":45,"area":null},{"id":"2310.12439","title":"PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models","created":"2023-10-19","cited_by_count":42,"area":"safety"},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40,"area":"safety"},{"id":"2406.06822","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","created":"2024-06-10","cited_by_count":40,"area":"safety"},{"id":"2210.15127","title":"Rethinking the Reverse-engineering of Trojan Triggers","created":"2022-10-27","cited_by_count":39,"area":"safety"},{"id":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"area":"safety"},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39,"area":"safety"},{"id":"2202.06382","title":"Training with More Confidence: Mitigating Injected and Natural Backdoors During Training","created":"2022-02-13","cited_by_count":38,"area":null},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"id":"2305.17826","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","created":"2023-05-28","cited_by_count":37,"area":"safety"},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2407.10887","title":"Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique","created":"2024-07-15","cited_by_count":37,"area":null},{"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":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34,"area":null},{"id":"2111.07608","title":"Property Inference Attacks Against GANs","created":"2021-11-15","cited_by_count":33,"area":"safety"},{"id":"2308.04451","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","created":"2023-08-04","cited_by_count":33,"area":"safety"},{"id":"2410.01264","title":"Backdooring Vision-Language Models with Out-Of-Distribution Data","created":"2024-10-02","cited_by_count":33,"area":"mllm"},{"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":"2201.07513","title":"Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders","created":"2022-01-19","cited_by_count":31,"area":null},{"id":"2312.00050","title":"Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift","created":"2023-11-27","cited_by_count":31,"area":"diffusion"},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28,"area":null},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2305.13257","title":"Watermarking Text Data on Large Language Models for Dataset Copyright","created":"2023-05-22","cited_by_count":27,"area":"safety"},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"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":"2206.01832","title":"Kallima: A Clean-label Framework for Textual Backdoor Attacks","created":"2022-06-03","cited_by_count":24,"area":"safety"},{"id":"2403.17155","title":"Task-Agnostic Detector for Insertion-Based Backdoor Attacks","created":"2024-03-25","cited_by_count":23,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"id":"2311.09763","title":"Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations","created":"2023-11-16","cited_by_count":21,"area":"safety"},{"id":"2402.02160","title":"Data Poisoning for In-context Learning","created":"2024-02-03","cited_by_count":21,"area":"safety"},{"id":"2405.11227","title":"BadActs: A Universal Backdoor Defense in the Activation Space","created":"2024-05-18","cited_by_count":21,"area":null},{"id":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20,"area":null},{"id":"2411.12701","title":"When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations","created":"2024-11-19","cited_by_count":20,"area":"safety"},{"id":"2305.17506","title":"Backdooring Neural Code Search","created":"2023-05-27","cited_by_count":19,"area":"safety"},{"id":"2308.02122","title":"ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP","created":"2023-08-04","cited_by_count":19,"area":"safety"},{"id":"2110.08247","title":"Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks","created":"2021-10-15","cited_by_count":18,"area":"safety"},{"id":"2305.18651","title":"UMD: Unsupervised Model Detection for X2X Backdoor Attacks","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2312.08667","title":"Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey","created":"2023-12-14","cited_by_count":18,"area":null},{"id":"2106.12478","title":"Teacher Model Fingerprinting Attacks Against Transfer Learning","created":"2021-06-23","cited_by_count":16,"area":null},{"id":"2301.10412","title":"BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing","created":"2023-01-25","cited_by_count":16,"area":"safety"},{"id":"2311.11225","title":"TextGuard: Provable Defense against Backdoor Attacks on Text Classification","created":"2023-11-19","cited_by_count":16,"area":"safety"},{"id":"2402.13459","title":"Learning to Poison Large Language Models for Downstream Manipulation","created":"2024-02-21","cited_by_count":16,"area":"lr"},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"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":"2111.04394","title":"Get a Model! Model Hijacking Attack Against Machine Learning Models","created":"2021-11-08","cited_by_count":14,"area":null},{"id":"2211.11958","title":"A Survey on Backdoor Attack and Defense in Natural Language Processing","created":"2022-11-22","cited_by_count":14,"area":"safety"},{"id":"2310.11397","title":"Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning","created":"2023-10-17","cited_by_count":14,"area":"safety"},{"id":"2310.18603","title":"Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers","created":"2023-10-28","cited_by_count":14,"area":"safety"},{"id":"2312.11513","title":"Maatphor: Automated Variant Analysis for Prompt Injection Attacks","created":"2023-12-12","cited_by_count":14,"area":"safety"},{"id":"2312.12768","title":"Mutual-modality Adversarial Attack with Semantic Perturbation","created":"2023-12-20","cited_by_count":14,"area":null},{"id":"2402.13532","title":"Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers","created":"2024-02-21","cited_by_count":14,"area":null},{"id":"2211.15929","title":"Backdoor Vulnerabilities in Normally Trained Deep Learning Models","created":"2022-11-29","cited_by_count":13,"area":null},{"id":"2404.02406","title":"Exploring Backdoor Vulnerabilities of Chat Models","created":"2024-04-03","cited_by_count":13,"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":"2303.14325","title":"Backdoor Attacks with Input-unique Triggers in NLP","created":"2023-03-25","cited_by_count":12,"area":"safety"},{"id":"2305.07406","title":"Two-in-One: A Model Hijacking Attack Against Text Generation Models","created":"2023-05-12","cited_by_count":12,"area":null},{"id":"2308.03906","title":"TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models","created":"2023-08-07","cited_by_count":12,"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":"2407.03160","title":"SOS! Soft Prompt Attack Against Open-Source Large Language Models","created":"2024-07-03","cited_by_count":10,"area":"safety"},{"id":"2210.00108","title":"ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2308.13904","title":"LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors","created":"2023-08-26","cited_by_count":9,"area":"safety"},{"id":"2409.14119","title":"Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm","created":"2024-09-21","cited_by_count":9,"area":null},{"id":"2410.02182","title":"BadCM: Invisible Backdoor Attack Against Cross-Modal Learning","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2510.27623","title":"BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning","created":"2025-10-31","cited_by_count":9,"area":"mllm"},{"id":"2303.01742","title":"NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning","created":"2023-03-03","cited_by_count":8,"area":"safety"},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"id":"2412.19037","title":"CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers","created":"2024-12-26","cited_by_count":8,"area":"safety"},{"id":"2502.15830","title":"Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness","created":"2025-02-20","cited_by_count":8,"area":"safety"},{"id":"2503.06453","title":"Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation","created":"2025-03-09","cited_by_count":8,"area":"diffusion"},{"id":"2508.02175","title":"Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers","created":"2025-08-04","cited_by_count":8,"area":"safety"},{"id":"2404.02356","title":"Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors","created":"2024-04-02","cited_by_count":7,"area":"moe"},{"id":"2408.08671","title":"Towards Physical World Backdoor Attacks against Skeleton Action Recognition","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2511.16709","title":"AutoBackdoor: Automating Backdoor Attacks via LLM Agents","created":"2025-11-20","cited_by_count":7,"area":"agents"}],"next_cursor":"100"}