Skip to content

Commit

Permalink
[MESL] add project info
Browse files Browse the repository at this point in the history
  • Loading branch information
Reapor-Yurnero committed Feb 9, 2025
1 parent ae05835 commit 8bd36b4
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 0 deletions.
6 changes: 6 additions & 0 deletions data/projectsData.ts
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,12 @@ const projectsData: Project[] = [
imgSrc: '/static/images/projects/llm-ltr-cover.jpg',
href: 'https://hao-ai-lab.github.io/blogs/vllm-ltr',
},
{
title: 'Imprompter: Tricking LLM Agents into Improper Tool Use',
description: `We contribute to the security foundations of agent-based systems and surface a new class of automatically computed obfuscated adversarial prompt attacks that violate the confidentiality and integrity of user resources connected to an LLM agent. We show an information exfiltration attack on Mistral's LeChat agent that analyzes a user's conversation, picks out personally identifiable information, and formats it into a valid markdown command that results in leaking that data to the attacker's server.`,
imgSrc: '/static/images/projects/imprompter.png',
href: 'https://imprompter.ai/',
},
{
title: "Can Scheduling Overhead Dominate LLM Inference Performance? A Study of CPU Scheduling Overhead on Two Popular LLM Inference Systems",
description: "CPU scheduling overhead can dominate LLM inference time—up to 50% in systems like vLLM! Scheduling overhead can no longer be ignored as model forwarding speeds increase and more scheduling tasks get added.",
Expand Down
Binary file added public/static/images/projects/imprompter.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 8bd36b4

Please sign in to comment.