arXiv subjects

Sahar Abdelnabi

Publications and source records attributed to Sahar Abdelnabi.

At least 37 records · Page 2Linked to original sources

arXiv2025

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central question to the field. We posit that CI demands a form of reasoning where the agent needs to reason about the context in which it is operating. To test this, we first prompt LLMs to reason explicitly about CI when deciding what information to disclose. We then extend this approach by developing a reinforcement learning (RL) framework that further instills in models the reasoning necessary to achieve CI. Using a synthetic, automatically created, dataset of only $\sim700$ examples but with diverse contexts and information disclosure norms, we show that our method substantially reduces inappropriate information disclosure while maintaining task performance across multiple model sizes and families. Importantly, improvements transfer from this synthetic dataset to established CI benchmarks such as PrivacyLens that has human annotations and evaluates privacy leakage of AI assistants in actions and tool calls. Our code is available at: https://github.com/EricGLan/CI-RL

cs.AI↗

arXiv2025

ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations

As language models evolve into autonomous agents that act and communicate on behalf of users, ensuring safety in multi-agent ecosystems becomes a central challenge. Interactions between personal assistants and external service providers expose a core tension between utility and protection: effective collaboration requires information sharing, yet every exchange creates new attack surfaces. We introduce ConVerse, a dynamic benchmark for evaluating privacy and security risks in agent-agent interactions. ConVerse spans three practical domains (travel, real estate, insurance) with 12 user personas and over 864 contextually grounded attacks (611 privacy, 253 security). Unlike prior single-agent settings, it models autonomous, multi-turn agent-to-agent conversations where malicious requests are embedded within plausible discourse. Privacy is tested through a three-tier taxonomy assessing abstraction quality, while security attacks target tool use and preference manipulation. Evaluating seven state-of-the-art models reveals persistent vulnerabilities; privacy attacks succeed in up to 88% of cases and security breaches in up to 60%, with stronger models leaking more. By unifying privacy and security within interactive multi-agent contexts, ConVerse reframes safety as an emergent property of communication.

cs.CR↗

arXiv2025

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based on instructions stored in simple markdown files. Although Agent Skills can be a very useful tool, we show that they are fundamentally insecure, since they enable trivially simple prompt injections. We demonstrate how to hide malicious instructions in long Agent Skill files and referenced scripts to exfiltrate sensitive data, such as internal files or passwords. Importantly, we show how to bypass system-level guardrails of a popular coding agent: a benign, task-specific approval with the "Don't ask again" option can carry over to closely related but harmful actions. Overall, we conclude that despite ongoing research efforts and scaling model capabilities, frontier LLMs remain vulnerable to very simple prompt injections in realistic scenarios. Our code is available at https://github.com/aisa-group/promptinject-agent-skills.

cs.LG↗

arXiv2025

The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness

Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more readily with harmful prompts if real-world consequences appear absent. We present the first quantitative study of how such "test awareness" impacts model behavior, particularly its performance on safety-related tasks. We introduce a white-box probing framework that (i) linearly identifies awareness-related activations and (ii) steers models toward or away from test awareness while monitoring downstream performance. We apply our method to different state-of-the-art open-weight reasoning LLMs across both realistic and hypothetical tasks (denoting tests or simulations). Our results demonstrate that test awareness significantly impacts safety alignment (such as compliance with harmful requests and conforming to stereotypes) with effects varying in both magnitude and direction across models. By providing control over this latent effect, our work aims to provide a stress-test mechanism and increase trust in how we perform safety evaluations.

cs.CL↗

arXiv2025

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies

A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable nuanced protocols that account for unstructured private data, user constraints, and preferences. However, this design introduces new risks, including misalignment and attacks by malicious parties that compromise agents or steal user data. In this paper, we propose the Terrarium framework for fine-grained study on safety, privacy, and security in LLM-based MAS. We repurpose the blackboard design, an early approach in multi-agent systems, to create a modular, configurable testbed for multi-agent collaboration. We identify key attack vectors such as misalignment, malicious agents, compromised communication, and data poisoning. We implement three collaborative MAS scenarios with four representative attacks to demonstrate the framework's flexibility. By providing tools to rapidly prototype, evaluate, and iterate on defenses and designs, Terrarium aims to accelerate progress toward trustworthy multi-agent systems.

cs.AI↗

arXiv2025

Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models

Representation Engineering (RepE) is a novel paradigm for controlling the behavior of LLMs. Unlike traditional approaches that modify inputs or fine-tune the model, RepE directly manipulates the model's internal representations. As a result, it may offer more effective, interpretable, data-efficient, and flexible control over models' behavior. We present the first comprehensive survey of RepE for LLMs, reviewing the rapidly growing literature to address key questions: What RepE methods exist and how do they differ? For what concepts and problems has RepE been applied? What are the strengths and weaknesses of RepE compared to other methods? To answer these, we propose a unified framework describing RepE as a pipeline comprising representation identification, operationalization, and control. We posit that while RepE methods offer significant potential, challenges remain, including managing multiple concepts, ensuring reliability, and preserving models' performance. Towards improving RepE, we identify opportunities for experimental and methodological improvements and construct a guide for best practices.

cs.LG↗

arXiv2025

Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables

Scientific discovery catalyzes human intellectual advances, driven by the cycle of hypothesis generation, experimental design, evaluation, and assumption refinement. Central to this process is causal inference, uncovering the mechanisms behind observed phenomena. While randomized experiments provide strong inferences, they are often infeasible due to ethical or practical constraints. However, observational studies are prone to confounding or mediating biases. While crucial, identifying such backdoor paths is expensive and heavily depends on scientists' domain knowledge to generate hypotheses. We introduce a novel benchmark where the objective is to complete a partial causal graph. We design a benchmark with varying difficulty levels with over 4000 queries. We show the strong ability of LLMs to hypothesize the backdoor variables between a cause and its effect. Unlike simple knowledge memorization of fixed associations, our task requires the LLM to reason according to the context of the entire graph.

cs.LG↗

arXiv2025

A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive

Large Language Models (LLMs) are increasingly utilized in autonomous decision-making, where they sample options from vast action spaces. However, the heuristics that guide this sampling process remain under explored. We study this sampling behavior and show that this underlying heuristics resembles that of human decision-making: comprising a descriptive component (reflecting statistical norm) and a prescriptive component (implicit ideal encoded in the LLM) of a concept. We show that this deviation of a sample from the statistical norm towards a prescriptive component consistently appears in concepts across diverse real-world domains like public health, and economic trends. To further illustrate the theory, we demonstrate that concept prototypes in LLMs are affected by prescriptive norms, similar to the concept of normality in humans. Through case studies and comparison with human studies, we illustrate that in real-world applications, the shift of samples toward an ideal value in LLMs' outputs can result in significantly biased decision-making, raising ethical concerns.

cs.CL↗

arXiv2025

Get my drift? Catching LLM Task Drift with Activation Deltas

LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer queries based on relevant search results; email plugins summarize emails by processing their content through an LLM. However, the potentially untrusted provenance of these data sources can lead to prompt injection attacks, where the LLM is manipulated by natural language instructions embedded in the external data, causing it to deviate from the user's original instruction(s). We define this deviation as task drift. Task drift is a significant concern as it allows attackers to exfiltrate data or influence the LLM's output for other users. We study LLM activations as a solution to detect task drift, showing that activation deltas - the difference in activations before and after processing external data - are strongly correlated with this phenomenon. Through two probing methods, we demonstrate that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set. We evaluate these methods by making minimal assumptions about how users' tasks, system prompts, and attacks can be phrased. We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions, without being trained on any of these attacks. Interestingly, the fact that this solution does not require any modifications to the LLM (e.g., fine-tuning), as well as its compatibility with existing meta-prompting solutions, makes it cost-efficient and easy to deploy. To encourage further research on activation-based task inspection, decoding, and interpretability, we release our large-scale TaskTracker toolkit, featuring a dataset of over 500K instances, representations from six SoTA language models, and a suite of inspection tools.

cs.CR↗

arXiv2025

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Instruction-tuned Large Language Models (LLMs) show impressive results in numerous practical applications, but they lack essential safety features that are common in other areas of computer science, particularly an explicit separation of instructions and data. This makes them vulnerable to manipulations such as indirect prompt injections and generally unsuitable for safety-critical tasks. Surprisingly, there is currently no established definition or benchmark to quantify this phenomenon. In this work, we close this gap by introducing a formal measure for instruction-data separation and an empirical variant that is calculable from a model's outputs. We also present a new dataset, SEP, that allows estimating the measure for real-world models. Our results on various LLMs show that the problem of instruction-data separation is real: all models fail to achieve high separation, and canonical mitigation techniques, such as prompt engineering and fine-tuning, either fail to substantially improve separation or reduce model utility. The source code and SEP dataset are openly accessible at https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed.

cs.LG↗

arXiv2024

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt. The competition was organized in two phases. In the first phase, teams developed defenses to prevent the model from leaking the secret. During the second phase, teams were challenged to extract the secrets hidden for defenses proposed by the other teams. This report summarizes the main insights from the competition. Notably, we found that all defenses were bypassed at least once, highlighting the difficulty of designing a successful defense and the necessity for additional research to protect LLM systems. To foster future research in this direction, we compiled a dataset with over 137k multi-turn attack chats and open-sourced the platform.

cs.CR↗

arXiv2024

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation

There is an growing interest in using Large Language Models (LLMs) in multi-agent systems to tackle interactive real-world tasks that require effective collaboration and assessing complex situations. Yet, we still have a limited understanding of LLMs' communication and decision-making abilities in multi-agent setups. The fundamental task of negotiation spans many key features of communication, such as cooperation, competition, and manipulation potentials. Thus, we propose using scorable negotiation to evaluate LLMs. We create a testbed of complex multi-agent, multi-issue, and semantically rich negotiation games. To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities while integrating them in a dynamic and multi-turn setup. We propose multiple metrics to rigorously quantify agents' performance and alignment with the assigned role. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark. Importantly, we evaluate critical safety aspects such as the interaction dynamics between agents influenced by greedy and adversarial players. Our benchmark is highly challenging; GPT-3.5 and small models mostly fail, and GPT-4 and SoTA large models (e.g., Llama-3 70b) still underperform.

cs.CL↗

arXiv2023

From Attachments to SEO: Click Here to Learn More about Clickbait PDFs!

Clickbait PDFs are PDF documents that do not embed malware but trick victims into visiting malicious web pages leading to attacks like password theft or drive-by download. While recent reports indicate a surge of clickbait PDFs, prior works have largely neglected this new threat, considering PDFs only as accessories of email phishing campaigns. This paper investigates the landscape of clickbait PDFs and presents the first systematic and comprehensive study of this phenomenon. Starting from a real-world dataset, we identify 44 clickbait PDF clusters via clustering and characterize them by looking at their volumetric, temporal, and visual features. Among these, we identify three large clusters covering 89% of the dataset, exhibiting significantly different volumetric and temporal properties compared to classical email phishing, and relying on web UI elements as visual baits. Finally, we look at the distribution vectors and show that clickbait PDFs are not only distributed via attachments but also via Search Engine Optimization attacks, placing clickbait PDFs outside the email distribution ecosystem. Clickbait PDFs seem to be a lurking threat, not subjected to any form of content-based filtering or detection: AV scoring systems, like VirusTotal, rank them considerably low, creating a blind spot for organizations. While URL blocklists can help to prevent victims from visiting the attack web pages, we observe that they have a limited coverage.

cs.CR↗

arXiv2023

Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems

Mis- and disinformation are a substantial global threat to our security and safety. To cope with the scale of online misinformation, researchers have been working on automating fact-checking by retrieving and verifying against relevant evidence. However, despite many advances, a comprehensive evaluation of the possible attack vectors against such systems is still lacking. Particularly, the automated fact-verification process might be vulnerable to the exact disinformation campaigns it is trying to combat. In this work, we assume an adversary that automatically tampers with the online evidence in order to disrupt the fact-checking model via camouflaging the relevant evidence or planting a misleading one. We first propose an exploratory taxonomy that spans these two targets and the different threat model dimensions. Guided by this, we design and propose several potential attack methods. We show that it is possible to subtly modify claim-salient snippets in the evidence and generate diverse and claim-aligned evidence. Thus, we highly degrade the fact-checking performance under many different permutations of the taxonomy's dimensions. The attacks are also robust against post-hoc modifications of the claim. Our analysis further hints at potential limitations in models' inference when faced with contradicting evidence. We emphasize that these attacks can have harmful implications on the inspectable and human-in-the-loop usage scenarios of such models, and we conclude by discussing challenges and directions for future defenses.

cs.CR↗

arXiv2023

From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency

We outline a planned experiment to investigate if personal data (e.g., demographics and behavioral patterns) can be used to selectively expose individuals to disinformation such that an adversary can spread disinformation more efficiently compared to broadcasting the same information to everyone. This mechanism, if effective, will have devastating consequences as modern technologies collect and infer a plethora of private data that can be abused to target with disinformation. We believe this research will inform designing policies and regulations for online platforms.

cs.CR↗

arXiv2023

Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial prompting, e.g., Prompt Injection (PI) attacks enable attackers to override original instructions and employed controls. So far, it was assumed that the user is directly prompting the LLM. But, what if it is not the user prompting? We argue that LLM-Integrated Applications blur the line between data and instructions. We reveal new attack vectors, using Indirect Prompt Injection, that enable adversaries to remotely (without a direct interface) exploit LLM-integrated applications by strategically injecting prompts into data likely to be retrieved. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities, including data theft, worming, information ecosystem contamination, and other novel security risks. We demonstrate our attacks' practical viability against both real-world systems, such as Bing's GPT-4 powered Chat and code-completion engines, and synthetic applications built on GPT-4. We show how processing retrieved prompts can act as arbitrary code execution, manipulate the application's functionality, and control how and if other APIs are called. Despite the increasing integration and reliance on LLMs, effective mitigations of these emerging threats are currently lacking. By raising awareness of these vulnerabilities and providing key insights into their implications, we aim to promote the safe and responsible deployment of these powerful models and the development of robust defenses that protect users and systems from potential attacks.

cs.CR↗

arXiv2022

Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources

Misinformation is now a major problem due to its potential high risks to our core democratic and societal values and orders. Out-of-context misinformation is one of the easiest and effective ways used by adversaries to spread viral false stories. In this threat, a real image is re-purposed to support other narratives by misrepresenting its context and/or elements. The internet is being used as the go-to way to verify information using different sources and modalities. Our goal is an inspectable method that automates this time-consuming and reasoning-intensive process by fact-checking the image-caption pairing using Web evidence. To integrate evidence and cues from both modalities, we introduce the concept of 'multi-modal cycle-consistency check'; starting from the image/caption, we gather textual/visual evidence, which will be compared against the other paired caption/image, respectively. Moreover, we propose a novel architecture, Consistency-Checking Network (CCN), that mimics the layered human reasoning across the same and different modalities: the caption vs. textual evidence, the image vs. visual evidence, and the image vs. caption. Our work offers the first step and benchmark for open-domain, content-based, multi-modal fact-checking, and significantly outperforms previous baselines that did not leverage external evidence.

cs.CV↗

arXiv2022

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual misinformation. While existing research work on deepfake detection demonstrates high accuracy, it is subject to advances in generation techniques and adversarial iterations on detection countermeasure techniques. Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models. Our approach is simple and effective. We first embed artificial fingerprints into training data, then validate a surprising discovery on the transferability of such fingerprints from training data to generative models, which in turn appears in the generated deepfakes. Experiments show that our fingerprinting solution (1) holds for a variety of cutting-edge generative models, (2) leads to a negligible side effect on generation quality, (3) stays robust against image-level and model-level perturbations, (4) stays hard to be detected by adversaries, and (5) converts deepfake detection and attribution into trivial tasks and outperforms the recent state-of-the-art baselines. Our solution closes the responsibility loop between publishing pre-trained generative model inventions and their possible misuses, which makes it independent of the current arms race. Code and models are available at https://github.com/ningyu1991/ArtificialGANFingerprints .

cs.CR↗