3 accepted papers
A key tool in developing safe AI models is *data auditing*, i.e., using statistical tools to determine whether harmful content may have been used in the training data of a black-box model. Unfortunately, most *membership inference attacks* (MIAs) used to perform this type of auditing themselves assu…
Modern artificial intelligence (AI) systems have transformative potential across many domains, but also present profound new risks to child safety. AI is increasingly being misused to create AI-generated child sexual abuse material, facilitate child sexual exploitation, and reduce barriers to harm. …
We stress test monitoring systems for detecting covert misbehavior in LLM agents (e.g., secretly exfiltrating data). We propose a monitor red teaming (MRT) workflow that varies agent and monitor awareness, adversarial evasion strategies, and evaluation across tool-calling (SHADE-Arena) and computer-…