5 papers · 1 filter
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…
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…
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…
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…
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…