Alexandra Souly is a researcher who contributed to work on AI jailbreaks presented at NeurIPS 2024.
How this journalist typically writes
Alexandra Souly as author
Anthropic's joint study reveals that as few as 250 malicious documents can create backdoor vulnerabilities in large language models regardless of model size, challenging assumptions that attackers need to control a percentage of training data.
“Author of "Anthropic Battles Poisoned Data, Branding Blitz, and Legal Bills" in Anthropic”