{"total":222,"rows":[{"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":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"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":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145,"area":"safety"},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137,"area":"agents"},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"id":"2406.03007","title":"BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents","created":"2024-06-05","cited_by_count":115,"area":"agents"},{"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":"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":"2305.01219","title":"Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models","created":"2023-05-02","cited_by_count":94,"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":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74,"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":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66,"area":"safety"},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63,"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":"2401.05949","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","created":"2024-01-11","cited_by_count":53,"area":"safety"},{"id":"2110.12925","title":"CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning","created":"2021-10-25","cited_by_count":47,"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":"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":"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":"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":"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":"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":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"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":"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":"2310.14480","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","created":"2023-10-23","cited_by_count":32,"area":"safety"},{"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":"2306.06815","title":"TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models","created":"2023-06-12","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":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28,"area":null},{"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":"2404.01907","title":"Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack","created":"2024-04-02","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":"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":"2402.19334","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":"2205.12331","title":"Certified Robustness Against Natural Language Attacks by Causal Intervention","created":"2022-05-24","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":"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":"2410.14479","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","created":"2024-10-18","cited_by_count":22,"area":"rag"},{"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":"2311.09763","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":"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":"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":"2506.16447","title":"Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"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":"2305.16617","title":"Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model","created":"2023-05-26","cited_by_count":18,"area":null},{"id":"2503.00596","title":"BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge","created":"2025-03-01","cited_by_count":18,"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":"2506.11113","title":"Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks","created":"2025-06-08","cited_by_count":16,"area":null},{"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":"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":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"id":"2505.12567","title":"A Survey of Attacks on Large Language Models","created":"2025-05-18","cited_by_count":15,"area":"agents"},{"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":"2402.13532","title":"Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers","created":"2024-02-21","cited_by_count":14,"area":null},{"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":"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":"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":"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":"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":"2405.07667","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","created":"2024-05-13","cited_by_count":12,"area":"safety"},{"id":"2210.17029","title":"Poison Attack and Defense on Deep Source Code Processing Models","created":"2022-10-31","cited_by_count":11,"area":"safety"},{"id":"2503.08704","title":"Life-Cycle Routing Vulnerabilities of LLM Router","created":"2025-03-09","cited_by_count":11,"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":"2312.10467","title":"TrojFSP: Trojan Insertion in Few-shot Prompt Tuning","created":"2023-12-16","cited_by_count":9,"area":null},{"id":"2409.00399","title":"Rethinking Backdoor Detection Evaluation for Language Models","created":"2024-08-31","cited_by_count":9,"area":"lr"},{"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":"2507.01321","title":"ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks","created":"2025-07-02","cited_by_count":9,"area":"safety"},{"id":"2508.01365","title":"ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models","created":"2025-08-02","cited_by_count":9,"area":"safety"},{"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"}],"next_cursor":"100"}