{"total":131,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269,"area":null},{"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":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155,"area":null},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131,"area":"agents"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101,"area":null},{"id":"2403.17336","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","created":"2024-03-26","cited_by_count":86,"area":"safety"},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"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":"2112.05224","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","created":"2021-12-09","cited_by_count":73,"area":"safety"},{"id":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65,"area":null},{"id":"2301.02344","title":"TrojanPuzzle: Covertly Poisoning Code-Suggestion Models","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2301.02496","title":"Stealthy Backdoor Attack for Code Models","created":"2023-01-06","cited_by_count":49,"area":"safety"},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"area":null},{"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":"2105.01622","title":"Poisoning the Unlabeled Dataset of Semi-Supervised Learning","created":"2021-05-04","cited_by_count":44,"area":null},{"id":"2110.06904","title":"Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks","created":"2021-10-13","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":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2205.06401","title":"PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning","created":"2022-05-13","cited_by_count":34,"area":"safety"},{"id":"2308.14401","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","created":"2023-08-28","cited_by_count":34,"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":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2408.02882","title":"Compromising Embodied Agents with Contextual Backdoor Attacks","created":"2024-08-06","cited_by_count":31,"area":"agents"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2106.05784","title":"Programming Puzzles","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2110.09610","title":"A Survey on Machine Learning Techniques for Source Code Analysis","created":"2021-10-18","cited_by_count":24,"area":null},{"id":"2306.08350","title":"Multi-target Backdoor Attacks for Code Pre-trained Models","created":"2023-06-14","cited_by_count":23,"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":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"id":"2301.10416","title":"AI vs. Human -- Differentiation Analysis of Scientific Content Generation","created":"2023-01-24","cited_by_count":21,"area":null},{"id":"2503.22759","title":"Data Poisoning in Deep Learning: A Survey","created":"2025-03-27","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":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2502.01853","title":"Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis","created":"2025-02-03","cited_by_count":19,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2411.17569","title":"RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation","created":"2024-11-26","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":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2408.02509","title":"Black-Box Adversarial Attacks on LLM-Based Code Completion","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2209.05948","title":"Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems","created":"2022-09-13","cited_by_count":13,"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":"2409.19182","title":"Artificial-Intelligence Generated Code Considered Harmful: A Road Map for Secure and High-Quality Code Generation","created":"2024-09-27","cited_by_count":12,"area":null},{"id":"2506.02089","title":"SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design","created":"2025-06-02","cited_by_count":12,"area":"safety"},{"id":"2503.13116","title":"VeriLeaky: Navigating IP Protection vs Utility in Fine-Tuning for LLM-Driven Verilog Coding","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2412.15004","title":"From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2310.01423","title":"An Empirical Study of AI Generated Text Detection Tools","created":"2023-09-27","cited_by_count":9,"area":null},{"id":"2310.17903","title":"Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey","created":"2023-10-27","cited_by_count":9,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"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":"2506.06518","title":"A Systematic Review of Poisoning Attacks Against Large Language Models","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2507.19598","title":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2403.06675","title":"Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code","created":"2024-03-11","cited_by_count":6,"area":"safety"},{"id":"2107.10443","title":"Spinning Sequence-to-Sequence Models with Meta-Backdoors","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2210.04802","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2305.09438","title":"MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2407.11072","title":"MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2408.04683","title":"Eliminating Backdoors in Neural Code Models for Secure Code Understanding","created":"2024-08-08","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":"2510.16558","title":"A First Look at the Security Issues in the Model Context Protocol Ecosystem","created":"2025-10-18","cited_by_count":5,"area":"agents"},{"id":"2302.06801","title":"Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions","created":"2023-02-14","cited_by_count":4,"area":"safety"},{"id":"2405.11466","title":"Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code","created":"2024-05-19","cited_by_count":4,"area":"safety"},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","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":"2607.08011","title":"Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions","created":"2026-07-09","cited_by_count":4,"area":"safety"},{"id":"2203.15506","title":"Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning","created":"2022-03-25","cited_by_count":3,"area":null},{"id":"2503.07697","title":"PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"safety"},{"id":"2508.17361","title":"Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias","created":"2025-08-24","cited_by_count":3,"area":null},{"id":"2602.04195","title":"Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation","created":"2026-02-04","cited_by_count":3,"area":"safety"},{"id":"2603.14225","title":"\"I'm Not Reading All of That\": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants","created":"2026-03-15","cited_by_count":3,"area":"agents"},{"id":"2605.23168","title":"PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2209.14013","title":"On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach","created":"2022-09-28","cited_by_count":2,"area":"safety"},{"id":"2211.11711","title":"CLAWSAT: Towards Both Robust and Accurate Code Models","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2212.10318","title":"Learned-Database Systems Security","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2404.18567","title":"Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks","created":"2024-04-29","cited_by_count":2,"area":"safety"},{"id":"2405.02828","title":"Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2407.19216","title":"EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection","created":"2024-07-27","cited_by_count":2,"area":null},{"id":"2509.02372","title":"Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2603.02436","title":"TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":"safety"},{"id":"2402.12936","title":"Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERT","created":"2024-02-20","cited_by_count":1,"area":"safety"},{"id":"2402.16896","title":"On Trojan Signatures in Large Language Models of Code","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2408.00129","title":"Vera Verto: Multimodal Hijacking Attack","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2409.13004","title":"Data Poisoning and Leakage Analysis in Federated Learning","created":"2024-09-19","cited_by_count":1,"area":"safety"},{"id":"2503.17578","title":"Large Language Models Can Verbatim Reproduce Long Malicious Sequences","created":"2025-03-21","cited_by_count":1,"area":"safety"},{"id":"2506.01825","title":"Backdoors in Code Summarizers: How Bad Is It?","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2507.01487","title":"How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","cited_by_count":1,"area":"safety"}],"next_cursor":"100"}