{"total":71,"rows":[{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443,"area":"safety"},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725,"area":"safety"},{"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":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431,"area":"alignment"},{"id":"2503.18813","title":"Defeating Prompt Injections by Design","created":"2025-03-24","cited_by_count":297,"area":"agents"},{"id":"2310.10669","title":"Unbiased Watermark for Large Language Models","created":"2023-09-22","cited_by_count":111,"area":"safety"},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95,"area":"safety"},{"id":"2407.20859","title":"Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification","created":"2024-07-30","cited_by_count":81,"area":"agents"},{"id":"2307.10719","title":"LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?","created":"2023-07-20","cited_by_count":49,"area":null},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2208.04135","title":"Adversarial Attacks on Image Generation With Made-Up Words","created":"2022-08-04","cited_by_count":32,"area":null},{"id":"2302.04116","title":"Training-free Lexical Backdoor Attacks on Language Models","created":"2023-02-08","cited_by_count":31,"area":"safety"},{"id":"2209.08891","title":"Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis","created":"2022-09-19","cited_by_count":29,"area":"diffusion"},{"id":"2205.13618","title":"Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors","created":"2022-05-26","cited_by_count":28,"area":null},{"id":"2206.07840","title":"Architectural Backdoors in Neural Networks","created":"2022-06-15","cited_by_count":25,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2302.05706","title":"MTTM: Metamorphic Testing for Textual Content Moderation Software","created":"2023-02-11","cited_by_count":22,"area":null},{"id":"2506.09956","title":"LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge","created":"2025-06-11","cited_by_count":21,"area":"safety"},{"id":"2209.03755","title":"Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems","created":"2022-09-07","cited_by_count":12,"area":null},{"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":"2402.06957","title":"Architectural Neural Backdoors from First Principles","created":"2024-02-10","cited_by_count":11,"area":null},{"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":"2303.07320","title":"Model-tuning Via Prompts Makes NLP Models Adversarially Robust","created":"2023-03-13","cited_by_count":9,"area":null},{"id":"2403.11297","title":"A Modified Word Saliency-Based Adversarial Attack on Text Classification Models","created":"2024-03-17","cited_by_count":9,"area":null},{"id":"2207.00694","title":"Efficient Adversarial Training With Data Pruning","created":"2022-07-01","cited_by_count":7,"area":null},{"id":"2303.14443","title":"No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning","created":"2023-03-25","cited_by_count":7,"area":null},{"id":"2304.10727","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","created":"2023-04-21","cited_by_count":7,"area":"mllm"},{"id":"2403.18587","title":"The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2408.13461","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","created":"2024-08-24","cited_by_count":7,"area":"mllm"},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2206.04137","title":"Adversarial Text Normalization","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2306.07033","title":"When Vision Fails: Text Attacks Against ViT and OCR","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2401.17133","title":"SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers","created":"2024-01-30","cited_by_count":5,"area":null},{"id":"2310.19152","title":"BERT Lost Patience Won't Be Robust to Adversarial Slowdown","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2504.08798","title":"Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2510.11195","title":"RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"id":"2601.13082","title":"Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Trading","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2210.13289","title":"Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2211.15363","title":"On the Security Vulnerabilities of Text-to-SQL Models","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2303.05077","title":"Learning the Legibility of Visual Text Perturbations","created":"2023-03-09","cited_by_count":3,"area":null},{"id":"2306.05079","title":"Enhancing Robustness of AI Offensive Code Generators via Data Augmentation","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2404.09481","title":"SpamDam: Towards Privacy-Preserving and Adversary-Resistant SMS Spam Detection","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2410.15396","title":"The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2412.21123","title":"ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation","created":"2024-12-30","cited_by_count":3,"area":"safety"},{"id":"2501.12174","title":"BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks","created":"2025-01-21","cited_by_count":3,"area":"safety"},{"id":"2203.02958","title":"Towards a Responsible AI Development Lifecycle: Lessons From Information Security","created":"2022-03-06","cited_by_count":2,"area":null},{"id":"2312.02220","title":"QuantAttack: Exploiting Dynamic Quantization to Attack Vision Transformers","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2402.02554","title":"DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2505.06454","title":"Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2506.08188","title":"GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2602.02569","title":"DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2212.03980","title":"DDoD: Dual Denial of Decision Attacks on Human-AI Teams","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2304.07980","title":"RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks","created":"2023-04-17","cited_by_count":1,"area":null},{"id":"2306.03600","title":"Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations","created":"2023-06-06","cited_by_count":1,"area":"safety"},{"id":"2310.08259","title":"Invisible Threats: Backdoor Attack in OCR Systems","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2412.08098","title":"What You See Is Not Always What You Get: Evaluating GPT's Comprehension of Source Code","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2505.03831","title":"A Comprehensive Analysis of Adversarial Attacks against Spam Filters","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2510.06530","title":"From Description to Detection: LLM based Extendable O-RAN Compliant Blind DoS Detection in 5G and Beyond","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.26847","title":"Broken-Token: Filtering Obfuscated Prompts by Counting Characters-Per-Token","created":"2025-10-30","cited_by_count":1,"area":"safety"},{"id":"2107.14601","title":"Who's Afraid of Thomas Bayes?","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2109.01558","title":"Learning Neural Models for Natural Language Processing in the Face of Distributional Shift","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2310.03358","title":"Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2407.14206","title":"Watermark Smoothing Attacks against Language Models","created":"2024-07-19","cited_by_count":0,"area":"safety"},{"id":"2410.13193","title":"Golyadkin's Torment: Doppelg\\\"angers and Adversarial Vulnerability","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2503.08226","title":"A Grey-box Text Attack Framework using Explainable AI","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2511.20944","title":"Semantic Superiority vs. Forensic Efficiency: A Comparative Analysis of Deep Learning and Psycholinguistics for Business Email Compromise Detection","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2512.02567","title":"Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2606.12978","title":"Trajectory-Level Redirection Attacks on Vision-Language-Action Models","created":"2026-06-11","cited_by_count":0,"area":"vla"},{"id":"2608.13100","title":"Multi-Layer Context Camouflaging: A Semantic Superposition and Contextual Lamination Framework for Malpractice-Resilient Online Assessment","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.33003","title":"Certified Interface Aliases: Exact Collisions in Vision-Language Preprocessing, and When They Exist","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}