19 citations · 40 across the 12 of their papers we have counts for
5 papers · 1 filter
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…
LlamaFirewall: An open source guardrail system for building secure AI agents
Sahana Chennabasappa, Cyrus Nikolaidis, Daniel Song +16
Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows,…
CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Shengye Wan, Cyrus Nikolaidis, Daniel Song +10
We are releasing a new suite of security benchmarks for LLMs, CYBERSECEVAL 3, to continue the conversation on empirically measuring LLM cybersecurity risks and capabilities. CYBERS…
CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
Manish Bhatt, Sahana Chennabasappa, Yue Li +10
Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel be…
Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Manish Bhatt, Sahana Chennabasappa, Cyrus Nikolaidis +18
This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants. As what we be…