Supply Chain Attacks
7 resourcesAttacks & Threats
Model supply chain, plugin, and dependency attacks
Poisoning Web-Scale Training Datasets is Practical
Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo + 6 more — IEEE S&P 2024
Demonstrates practical attacks to poison web-scale datasets like LAION by purchasing expired domains, affecting 0.01% of a dataset for under $60.
Security of AI-Based Code Generation Tools: A Multi-Perspective Study
Xinyi Hou, Yanjie Zhao, Yue Liu + 7 more — IEEE TSE
Examines security implications of AI code generation tools, analyzing vulnerability introduction patterns and mitigation strategies.
Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Manish Bhatt, Sahana Chennabasappa, Cyrus Nikolaidis + 2 more — arXiv preprint
Introduces CyberSecEval, a benchmark for evaluating the cybersecurity risks of LLM code generation, including insecure code suggestions.
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
Jiaqi Xue, Mengxin Zheng, Ting Hua + 4 more — NeurIPS 2023
Proposes TrojLLM, a black-box attack that generates universal trojan prompts to compromise LLMs without access to model internals.
AI Supply Chain Attacks and Mitigations: A Security-Focused Survey
Eitan Borgnia, Vinay Prabhu — IEEE S&P Workshop
Surveys the AI/ML supply chain attack surface including model repositories, training pipelines, and dependency risks, with practical mitigations.
GPT in Sheep's Clothing: The Risk of Customized GPTs
Tao Qin, Zhen Li, Wenxin Mao + 1 more — arXiv preprint
Analyzes security risks of custom GPTs in the OpenAI GPT Store including prompt leakage, data exfiltration, and malicious GPTs.
ConfusedPilot: Confused Deputy Attacks Against RAG-based Code Assistants
Andrew Patel, Hossein Aboutorab, Ilia Kolochenko — arXiv preprint
Introduces confused deputy attacks against RAG-based code assistants like GitHub Copilot, where poisoned code repositories manipulate assistant outputs.