{"total":227,"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":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222,"area":"safety"},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158,"area":"safety"},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157,"area":"safety"},{"id":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145,"area":"safety"},{"id":"2108.00352","title":"BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning","created":"2021-08-01","cited_by_count":123,"area":"safety"},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113,"area":null},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110,"area":"safety"},{"id":"2103.15543","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","created":"2021-03-29","cited_by_count":105,"area":"safety"},{"id":"2110.07831","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","created":"2021-10-15","cited_by_count":104,"area":"safety"},{"id":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96,"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":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90,"area":"safety"},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89,"area":"safety"},{"id":"2110.02467","title":"BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models","created":"2021-10-06","cited_by_count":85,"area":"safety"},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76,"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":"2401.12255","title":"Instructional Fingerprinting of Large Language Models","created":"2024-01-21","cited_by_count":68,"area":null},{"id":"2209.06015","title":"Black-box Dataset Ownership Verification via Backdoor Watermarking","created":"2022-08-04","cited_by_count":65,"area":null},{"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":"2103.04264","title":"T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification","created":"2021-03-07","cited_by_count":60,"area":"safety"},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2204.05239","title":"Exploring the Universal Vulnerability of Prompt-based Learning Paradigm","created":"2022-04-11","cited_by_count":57,"area":null},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57,"area":"safety"},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"id":"2109.08266","title":"Hard to Forget: Poisoning Attacks on Certified Machine Unlearning","created":"2021-09-17","cited_by_count":52,"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":"2406.18844","title":"Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift","created":"2024-06-27","cited_by_count":49,"area":"mllm"},{"id":"2205.08305","title":"A Study of the Attention Abnormality in Trojaned BERTs","created":"2022-05-13","cited_by_count":48,"area":null},{"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":"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":"2107.14569","title":"Can You Hear It? Backdoor Attacks via Ultrasonic Triggers","created":"2021-07-30","cited_by_count":44,"area":null},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42,"area":null},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"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":"2112.07668","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","created":"2021-12-14","cited_by_count":37,"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":"2111.12965","title":"Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks","created":"2021-11-25","cited_by_count":34,"area":null},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2309.13256","title":"Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks","created":"2023-09-23","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":"2310.14480","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","created":"2023-10-23","cited_by_count":32,"area":"safety"},{"id":"2311.09641","title":"RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models","created":"2023-11-16","cited_by_count":32,"area":"alignment"},{"id":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31,"area":"safety"},{"id":"2402.14968","title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","created":"2024-02-22","cited_by_count":31,"area":null},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29,"area":"alignment"},{"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":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2410.14425","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","created":"2024-10-18","cited_by_count":27,"area":"safety"},{"id":"2402.19334","title":"Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge","created":"2024-02-29","cited_by_count":26,"area":null},{"id":"2305.02394","title":"Defending against Insertion-based Textual Backdoor Attacks via Attribution","created":"2023-05-03","cited_by_count":25,"area":"safety"},{"id":"2109.01300","title":"How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data","created":"2021-09-03","cited_by_count":24,"area":null},{"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":"2107.05243","title":"Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning","created":"2021-07-12","cited_by_count":21,"area":"safety"},{"id":"2305.02424","title":"Backdoor Learning on Sequence to Sequence Models","created":"2023-05-03","cited_by_count":21,"area":null},{"id":"2305.11596","title":"Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation","created":"2023-05-19","cited_by_count":21,"area":null},{"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":"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":"2405.11227","title":"BadActs: A Universal Backdoor Defense in the Activation Space","created":"2024-05-18","cited_by_count":21,"area":null},{"id":"2106.07798","title":"Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers","created":"2021-06-14","cited_by_count":20,"area":"safety"},{"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":"2109.10855","title":"BFClass: A Backdoor-free Text Classification Framework","created":"2021-09-22","cited_by_count":19,"area":"safety"},{"id":"2210.07907","title":"Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks","created":"2022-10-14","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":"2310.18633","title":"Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots","created":"2023-10-28","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":"2410.02195","title":"BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2202.07183","title":"A Survey of Neural Trojan Attacks and Defenses in Deep Learning","created":"2022-02-15","cited_by_count":17,"area":null},{"id":"2202.08578","title":"An Equivalence Between Data Poisoning and Byzantine Gradient Attacks","created":"2022-02-17","cited_by_count":16,"area":"safety"},{"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":"2402.12168","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","created":"2024-02-19","cited_by_count":16,"area":null},{"id":"2402.13459","title":"Learning to Poison Large Language Models for Downstream Manipulation","created":"2024-02-21","cited_by_count":16,"area":"lr"},{"id":"2205.11803","title":"WeDef: Weakly Supervised Backdoor Defense for Text Classification","created":"2022-05-24","cited_by_count":15,"area":"safety"},{"id":"2305.16503","title":"IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks","created":"2023-05-25","cited_by_count":15,"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":"2210.07588","title":"Distributed Distributionally Robust Optimization with Non-Convex Objectives","created":"2022-10-14","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":"2310.18603","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":"2404.19597","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","created":"2024-04-30","cited_by_count":14,"area":"safety"},{"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":"2211.15929","title":"Backdoor Vulnerabilities in Normally Trained Deep Learning Models","created":"2022-11-29","cited_by_count":13,"area":null},{"id":"2409.01193","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","created":"2024-09-02","cited_by_count":13,"area":"safety"},{"id":"2505.14418","title":"Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents","created":"2025-05-20","cited_by_count":13,"area":"agents"},{"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":"2403.01472","title":"WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection","created":"2024-03-03","cited_by_count":12,"area":null},{"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":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2503.04036","title":"Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge","created":"2025-03-06","cited_by_count":12,"area":"safety"},{"id":"2503.08704","title":"Life-Cycle Routing Vulnerabilities of LLM Router","created":"2025-03-09","cited_by_count":11,"area":"safety"},{"id":"2112.03350","title":"Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks","created":"2021-12-06","cited_by_count":10,"area":null}],"next_cursor":"100"}