activity
20242026
collaborators
Showing 2025Show all

5 papers · 1 filter

cs.SE2025

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Thomas Kuntz, Agatha Duzan, Hao Zhao +4

Computer use agents are LLM-based agents that can directly interact with a graphical user interface, by processing screenshots or accessibility trees. While these systems are gaini…

cs.LG2025

Selective Induction Heads: How Transformers Select Causal Structures In Context

Francesco D'Angelo, Francesco Croce, Nicolas Flammarion

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, at…

cs.CL2025

Jailbreak Distillation: Renewable Safety Benchmarking

Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…

cs.CL2025

Is In-Context Learning Sufficient for Instruction Following in LLMs?

Hao Zhao, Maksym Andriushchenko, Francesco Croce +1

In-context learning (ICL) allows LLMs to learn from examples without changing their weights: this is a particularly promising capability for long-context LLMs that can potentially…

cs.CR2025

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs…