Exponential Security Labs

@expsecai

We build multi-agent safety & security environments for RL training and adaptive benchmarking.

Tübingen, Germany

expsec.ai

Joined May 2026

6 Following

531 Followers

Replies Reposts Media

Pinned
Exponential Security Labs
@expsecai
Sep 28
We're excited to announce our new work! Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct a sequence of actions taken by agents. These analyses assume that LLM agents cannot tamper with their own execution
Derck Prinzhorn
17
Exponential Security Labs
@expsecai
Oct 26
We are proud to share that our two new benchmarks, RepoInject v1 and BrowserInject v1, were used by Meta TBD Labs to report the robustness of Muse Spark 1.3 to prompt injections. The robustness of Muse Spark 1.3 is comparable to that of GPT-5.6 Sol—congrats to the team! 1/4
5
Exponential Security Labs
@expsecai
Sep 24
We're excited to announce a new paper! We find that many recent models end up evading monitors under ordinary task pressure. We introduce EvasionBench to measure this behavior. We find a very large variance in how models behave: from 88% evasion success of GLM-5.2 to 0% of
Derck Prinzhorn and 2 others
Exponential Security Labs
@expsecai
Jul 22
In our first research release at Exponential Security Labs, we built an automated, multi-turn and multi-lingual red-teaming system and tested recent open-weight and proprietary models on purpose-built regional jailbreak datasets.🧵
1
Exponential Security Labs
@expsecai
Jun 1
Today we are announcing our new startup: Exponential Security Labs. AI agents are being deployed everywhere, making high-stakes decisions and increasingly automating research itself. Yet their reliability and security remain unsolved technical problems, on a frontier that keeps
Naman D Singh and 2 others
3

Exponential Security Labs

Exponential Security Labs’s posts