collaborators

7 papers

cs.CR2026

Untrusted Content Masking for Web Agents with Security Guarantees

Kristina Nikolić, Egor Zverev, Javier Rando +3

Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such…

cs.AI2026

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

Hanna Foerster, Tom Blanchard, Kristina Nikolić +6

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior. Among proposed defenses, architectural isolation provides the strongest guaran…

cs.CV2026

Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?

Michael Aerni, Joshua Swanson, Kristina Nikolić +1

We present modal aphasia, a systematic dissociation in which current unified multimodal models accurately memorize concepts visually but fail to articulate them in writing, despite…

cs.AI2025

RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics

Jie Zhang, Cezara Petrui, Kristina Nikolić +1

Existing benchmarks for evaluating mathematical reasoning in large language models (LLMs) rely primarily on competition problems, formal proofs, or artificially challenging questio…

cs.LG2025

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs

Alexander Panfilov, Evgenii Kortukov, Kristina Nikolić +6

Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrifici…

cs.LG2025

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?

Kristina Nikolić, Luze Sun, Jie Zhang +1

Jailbreak attacks bypass the guardrails of large language models to produce harmful outputs. In this paper, we ask whether the model outputs produced by existing jailbreaks are act…