USENIX Security '24 - An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models:...

USENIX Security '24 - An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models:...Подробнее

USENIX Security '24 - Practical Data-Only Attack GenerationПодробнее

USENIX Security '24 - UBA-Inf: Unlearning Activated Backdoor Attack with Influence-Driven CamouflageПодробнее

USENIX Security '24 - SecurityNet: Assessing Machine Learning Vulnerabilities on Public ModelsПодробнее

USENIX Security '24 - Instruction Backdoor Attacks Against Customized LLMsПодробнее

USENIX Security '24 - Racing for TLS Certificate Validation: A Hijacker's Guide to the Android...Подробнее

USENIX Security '24 - Hijacking Attacks against Neural Network by Analyzing Training DataПодробнее

USENIX Security '24 - What Was Your Prompt? A Remote Keylogging Attack on AI AssistantsПодробнее

USENIX Security '21 - Graph BackdoorПодробнее

USENIX Security '23 - Aliasing Backdoor Attacks on Pre-trained ModelsПодробнее

USENIX Security '24 - Mudjacking: Patching Backdoor Vulnerabilities in Foundation ModelsПодробнее

USENIX Security '24 - EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability DetectionПодробнее

USENIX Security '21 - Blind Backdoors in Deep Learning ModelsПодробнее

USENIX Security '24 - PentestGPT: Evaluating and Harnessing Large Language Models for Automated...Подробнее

USENIX Security '24 - ModelGuard: Information-Theoretic Defense Against Model Extraction AttacksПодробнее

USENIX Security '24 - MD-ML: Super Fast Privacy-Preserving Machine Learning for Malicious...Подробнее

USENIX Security '23 - A Data-free Backdoor Injection Approach in Neural NetworksПодробнее

USENIX Security '24 - SnailLoad: Exploiting Remote Network Latency Measurements without JavaScriptПодробнее