Vikrant
You can extract the thinking process from closed LLMs
Researchers figured out how to steal the internal reasoning steps from proprietary models like GPT-4o and Claude through API timing attacks.
Read post
llm-security
3 posts tagged.
- llm-security
-
llm-securityVikrant
Agent Security Is a Systems Problem
A new paper argues that LLM agent security cannot be solved by better prompts or guardrails alone. The architecture itself leaks privilege.
Read post
-
prompt-injectionVikrant
The ChatGPT Google Sheets plugin leaks your data through prompt injection
A popular extension with 3 million users can be tricked into sending your spreadsheet contents to an attacker-controlled server. The fix is not obvious.
Read post