arXiv subjects

Kristina Nikolić

Publications and source records attributed to Kristina Nikolić.

7 recordsLinked to original sources

arXiv2026

Untrusted Content Masking for Web Agents with Security Guarantees

Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such as tool-use APIs, this separation arises naturally: agents can reason from interface definitions without ever processing untrusted content. Extending these guarantees to web agents faces a fundamental challenge: to perceive and interact with their environment, web agents must first observe the rendered page, which intermingles trusted content with untrusted content. This structural entanglement removes the trust boundary on which security guarantees depend, undermining provable defenses for web agents. In this paper, we present Untrusted Content Masking (UCM), a simple and effective approach that restores this boundary in web environments. We leverage a key structural insight: a webpage's Document Object Model (DOM) encodes sufficient information to distinguish trusted from untrusted regions without reading their content. Our framework exploits this by redacting untrusted regions before they reach the agent and routing interaction through a sandboxed interface with strict privilege separation, thereby enabling agents to observe and interact with their environment while remaining isolated from adversarial content. The code is publicly available.

cs.CR↗

arXiv2026

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

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior. Among proposed defenses, architectural isolation provides the strongest guarantees by strictly separating trusted task planning from untrusted environment observations. However, applying this design to Computer Use Agents (CUAs), which automate tasks by viewing screens and executing actions, presents a fundamental challenge. Current agents require continuous observation of UI state to determine each action, which conflicts with the isolation required for security. We resolve this tension by demonstrating that UI workflows, while dynamic, are structurally predictable. Single-shot planning, where a trusted planner emits upfront a complete branching plan covering all anticipated runtime states, provides control flow integrity guarantees against arbitrary instruction injections. We introduce NOVA (Navigating via Observation, Verification, and Action) to make this viable in the combinatorially large UI state space, where the plan can invoke a perception model to resolve runtime values such as UI coordinates. We evaluate our design on OSWorld, and retain up to 57% of the performance of frontier models while improving performance for smaller open-source models by up to 19%, demonstrating that rigorous security and utility can coexist in CUAs. Although upfront planning prevents instruction injections, we show that additional measures are needed to defend against \textbf{Branch Steering} attacks, where adversaries deceive the perception model into routing execution down attacker-preferred branches of the plan, such as redirecting the agent to a malicious website.

cs.AI↗

arXiv2026

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

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 being trained on images and text simultaneously. For one, we show that leading frontier models can generate near-perfect reproductions of iconic movie artwork, but confuse crucial details when asked for textual descriptions. We corroborate those findings through controlled experiments on synthetic datasets in multiple architectures. Our experiments confirm that modal aphasia reliably emerges as a fundamental property of current unified multimodal models, not just as a training artifact. In practice, modal aphasia can introduce vulnerabilities in AI safety frameworks, as safeguards applied to one modality may leave harmful concepts accessible in other modalities. We demonstrate this risk by showing how a model aligned solely on text remains capable of generating unsafe images.

cs.CV↗

arXiv2025

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

Existing benchmarks for evaluating mathematical reasoning in large language models (LLMs) rely primarily on competition problems, formal proofs, or artificially challenging questions -- failing to capture the nature of mathematics encountered in actual research environments. We introduce RealMath, a novel benchmark derived directly from research papers and mathematical forums that assesses LLMs' abilities on authentic mathematical tasks. Our approach addresses three critical challenges: sourcing diverse research-level content, enabling reliable automated evaluation through verifiable statements, and designing a continually refreshable dataset to mitigate contamination risks. Experimental results across multiple LLMs reveal surprising capabilities in handling research mathematics compared to competition problems, suggesting current models may already serve as valuable assistants for working mathematicians despite limitations on highly challenging problems. The code and dataset for RealMath are publicly available.

cs.AI↗

arXiv2025

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs

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, sacrificing helpfulness. We show that frontier LLMs can develop a preference for dishonesty as a new strategy, even when other options are available. Affected models respond to harmful requests with outputs that sound harmful but are crafted to be subtly incorrect or otherwise harmless in practice. This behavior emerges with hard-to-predict variations even within models from the same model family. We find no apparent cause for the propensity to deceive, but show that more capable models are better at executing this strategy. Strategic dishonesty already has a practical impact on safety evaluations, as we show that dishonest responses fool all output-based monitors used to detect jailbreaks that we test, rendering benchmark scores unreliable. Further, strategic dishonesty can act like a honeypot against malicious users, which noticeably obfuscates prior jailbreak attacks. While output monitors fail, we show that linear probes on internal activations can be used to reliably detect strategic dishonesty. We validate probes on datasets with verifiable outcomes and by using them as steering vectors. Overall, we consider strategic dishonesty as a concrete example of a broader concern that alignment of LLMs is hard to control, especially when helpfulness and harmlessness conflict.

cs.LG↗

arXiv2025

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?

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 actually useful. For example, when jailbreaking a model to give instructions for building a bomb, does the jailbreak yield good instructions? Since the utility of most unsafe answers (e.g., bomb instructions) is hard to evaluate rigorously, we build new jailbreak evaluation sets with known ground truth answers, by aligning models to refuse questions related to benign and easy-to-evaluate topics (e.g., biology or math). Our evaluation of eight representative jailbreaks across five utility benchmarks reveals a consistent drop in model utility in jailbroken responses, which we term the jailbreak tax. For example, while all jailbreaks we tested bypass guardrails in models aligned to refuse to answer math, this comes at the expense of a drop of up to 92% in accuracy. Overall, our work proposes the jailbreak tax as a new important metric in AI safety, and introduces benchmarks to evaluate existing and future jailbreaks. We make the benchmark available at https://github.com/ethz-spylab/jailbreak-tax

cs.LG↗

arXiv2025

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense

Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations at multiple noisy image resolutions, producing a single robust classification. This defense was shown to be effective against multiple state-of-the-art attacks. Perhaps even more convincingly, it was shown that the model's gradients are perceptually aligned: attacks against the model produce noise that perceptually resembles the targeted class. In this short note, we show that this defense is not robust to adversarial attack. We first show that the defense's randomness and ensembling method cause severe gradient masking. We then use standard adaptive attack techniques to reduce the defense's robust accuracy from 48% to 14% on CIFAR-100 and from 62% to 11% on CIFAR-10, under the $\ell_\infty$-norm threat model with $\varepsilon=8/255$.

cs.LG↗