Searcharxiv⌕ Search

arXiv subjects

Kamalika Chaudhuri

Publications and source records attributed to Kamalika Chaudhuri.

At least 19 recordsLinked to original sources

Scaling Adaptive Prompt Injection Attacks with Agent Swarms

Prompt injections have emerged as one of the top security risks faced by AI agents today. Early work in prompt injection attacks looked at simple tool-call agents and static attack payloads, and were saturated since mid-2025. As of Fall 2026, human red-teaming may be nearing saturation, especially on the Gemini family of models. In this work, we argue that despite this apparent plateau, prompt injection attacks are still possible and continued effort into prompt injection defense is needed. We design a new synthetic evaluation dataset which uses random non-malicious actions as adversarial goals. Such dataset design helps us to evaluate prompt injection robustness as a model ability to respect instruction hierarchy, and disentangle this ability from model knowledge of security practices. We show that an agentic attacker of increased capabilities can reliably trick model to follow instructions in tool output in our evaluation, even for models previously considered robust on public prompt injection benchmarks such as GraySwan Arena. This shows that current frontier defenses may require proactive, automated red-teaming to remain resilient to increasingly capable adversaries.

cs.CR↗

Agent Security is a Systems Problem

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness (the dominant viewpoint in the community) are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain. Based on our experience as cybersecurity researchers in operating systems, networks, formal methods, and adversarial machine learning, we articulate a set of core principles, grounded in decades of systems security research, that provide a foundation for designing agentic systems with predictable guarantees. As evidence, we analyze eleven representative real-world attacks on agents and discuss how systems principles, if realized, could have prevented these attacks. We also identify the research challenges that stand in the way of implementing these principles in agents.

cs.CR↗

Inadvertent Context Leakage in Language Models

For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether the mere presence of such secrets in a model's context window introduces hidden correlations into the model's benign outputs, allowing reconstruction even when the model correctly refuses direct extraction. We further study whether an adversary can actively engineer prompts that amplify this effect, using the model as a covert carrier to transmit secrets through seemingly innocuous text. In both cases, this limited leakage is exploited using a novel adaptive attack that assumes black-box access to the underlying model. In controlled experiments across eight proprietary models, we find that 2-digit in-context secrets are reconstructed with near-perfect accuracy and 4-digit secrets at 82\% exact match, all from outputs the model produces in response to ordinary, non-adversarial requests. We observe that more capable models leak more: stronger instruction-following amplifies sensitivity to in-context secrets, suggesting leakage is a byproduct of capability as opposed to a patchable bug. We show this leakage enables two practical attacks: (1) a trained classifier that infers semantic predicates about user memories (e.g., health conditions, financial events) from routine natural-language outputs, and (2) an RL-trained adversary that extracts full Social Security Numbers from a production-style agent.

cs.LG↗

InferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants

Large language model (LLM)-based personal agents are increasingly deployed to handle everyday tasks on users' behalf. These agents have access to private user information, while their tasks involve communicating with third parties; this raises a critical privacy concern that agents may inappropriately reveal sensitive user information to these recipients. Existing benchmarks primarily assess direct privacy leakage, where an agent explicitly states a pre-specified secret or attribute. However, they do not capture \textit{inferential leakage}, where the model leaves indirect cues in the reply that implicitly leaks sensitive attributes. We introduce \textsc{InferPriv}, a benchmark that measures whether an honest-but-curious recipient can infer a user's sensitive attributes from an LLM's reply on routine task. Evaluating five frontier models, we find that inferential leakage substantially exceeds direct leakage across models and prompts. Under a privacy-aware system prompt, GPT-6.1-Sol, Sonnet-5.5, and Gemini-3.8-Flash achieve near-zero direct leakage, yet the inferential leakage rate remains between 16.2--25.2\%. These findings suggest that evaluating explicit leakage alone can substantially understate the privacy risks.

cs.AI↗

Dataset Watermarking with Provable Black-Box Detection

Large Language Models (LLMs) are often pre-trained and post-trained on vast amounts of loosely curated data, and potentially have been trained on proprietary datasets or the benchmarks used for evaluation. This motivates dataset watermarking: designing datasets such that training on them leaves detectable signatures in the resulting model. Existing approaches embed watermarks by either injecting artificial content or paraphrasing full examples under token-level generation control, and many require model access beyond generated outputs for detection. Our method embeds a dataset-level watermark by increasing the co-occurrence of randomly selected word pairs through meaning-preserving local edits, and detects it from generated text alone with provable false positive control. We conduct evaluation on four base models and three datasets and show that it reliably detects the watermark ($p <0.01$) in the fine-tuning stage, outperforming existing black-box baselines. Our method remains effective under substantial dilution where watermarked data is less than 5% of fine-tuning tokens. Moreover, our method better preserves benchmark utility and semantic integrity than existing baselines.

cs.LG↗

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

Prompt injection is widely recognized as a major security threat to AI agents that interact with untrusted external data, such as websites, documents, and emails. Prior work has shown that, in the text domain, black-box prompt injection can achieve near-perfect attack success rates (ASRs). In the image domain, however, existing visual prompt injection methods are substantially less effective in attacking frontier commercial VLMs for materially harmful behavior. Achieving such outputs is hard because it requires a long and/or format-compliant target string, such as a precise, parseable native tool call with exact function names and arguments. We present Repeat-After-Me, a black-box adaptive visual prompt injection attack that can reveal personally identifiable information or make malicious tool calls. Across both open-weight and commercial frontier VLMs, including Qwen3.6-27B and GPT-5.5, our method achieves ASRs exceeding 82% and 47%, respectively, under a realistic setting in which the benign user prompt is semantically unrelated to the injected task and does not verbally authorize it. Our optimized injection has non-trivial attack transferability across commercial VLMs and benign samples. We show our attack works in cases where adaptive textual prompt injection fails. In a real-world OpenClaw agent connected to Discord, an untrusted user can use a minimally injected image from our attack to overwrite TOOLS.md, enabling future sensitive behaviors like remote code execution and secret exfiltration. We discuss potential defenses.

cs.CR↗

Metric Differential Privacy at the User-Level Via the Earth Mover's Distance

Metric differential privacy (DP) provides heterogeneous privacy guarantees based on a distance between the pair of inputs. It is a widely popular notion of privacy since it captures the natural privacy semantics for many applications (such as, for location data) and results in better utility than standard DP. However, prior work in metric DP has primarily focused on the item-level setting where every user only reports a single data item. A more realistic setting is that of user-level DP where each user contributes multiple items and privacy is then desired at the granularity of the user's entire contribution. In this paper, we initiate the study of one natural definition of metric DP at the user-level. Specifically, we use the earth-mover's distance ($d_\textsf{EM}$) as our metric to obtain a notion of privacy as it captures both the magnitude and spatial aspects of changes in a user's data. We make three main technical contributions. First, we design two novel mechanisms under $d_\textsf{EM}$-DP to answer linear queries and item-wise queries. Specifically, our analysis for the latter involves a generalization of the privacy amplification by shuffling result which may be of independent interest. Second, we provide a black-box reduction from the general unbounded to bounded $d_\textsf{EM}$-DP (size of the dataset is fixed and public) with a novel sampling based mechanism. Third, we show that our proposed mechanisms can provably provide improved utility over user-level DP, for certain types of linear queries and frequency estimation.

cs.CR↗

Alignment Defends LLMs from Property Inference Attacks

Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work has shown that such dataset-level information can be effectively extracted through property inference attacks, posing a confidentiality risk. Existing defenses against these attacks primarily operate by modifying the training data distribution and hence require access to the original data and retraining the model, limiting their applicability to settings where data is unavailable or models are already deployed. In this work, we propose alignment-based defenses for mitigating property inference attacks in LLMs. Our approach reshapes the model's output distribution towards a target property ratio via post-training alignment, without modifying the training data. In particular, we adapt two widely used RLHF frameworks--Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO)--as our defenses by constructing preference pairs and defining a specific reward function respectively. Through comprehensive experiments, we show that our alignment based defenses effectively mitigate property inference attacks while maintaining a strong utility confidentiality tradeoff.

cs.LG↗

Safety Alignment of LMs via Non-cooperative Games

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwise comparisons instead of point-wise scores, providing more robust supervision and potentially reducing reward hacking. Our RL recipe, AdvGame, shifts the Pareto frontier of safety and utility, yielding a Defender LM that is simultaneously more helpful and more resilient to adversarial attacks. In addition, the resulting Attacker LM converges into a strong, general-purpose red-teaming agent that can be directly deployed to probe arbitrary target models. Code at github.com/facebookresearch/advgame.

cs.AI↗

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy

Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely on specialized verification languages that demand substantial domain expertise or remain semi-automated and require human-in-the-loop guidance. In this work, we investigate whether large language models (LLMs) can automate DP reasoning. We introduce DPrivBench, a benchmark in which each instance asks whether a function or algorithm satisfies a stated DP guarantee under specified assumptions. The benchmark is carefully designed to cover a broad range of DP topics, span diverse difficulty levels, and resist shortcut reasoning through trivial pattern matching. Experiments show that while the strongest models handle textbook mechanisms well, all models struggle with advanced algorithms, revealing substantial gaps in current DP reasoning capabilities. Through further analytic study and failure-mode analysis, we identify several promising directions for improving automated DP reasoning. Our benchmark provides a solid foundation for developing and evaluating such methods, and complements existing benchmarks for mathematical reasoning.

cs.LG↗

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

cs.CR↗

Systems Security Foundations for Agentic Computing

In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools, such as web browsers, compilers, and more. However, despite their popularity, agentic AI systems also introduce a myriad of security concerns, due to their constant interaction with third-party servers. For example, a malicious adversary can cause data exfiltration by executing prompt injection attacks, as well as other unwarranted behavior. These security concerns have recently motivated researchers to improve the safety and reliability of agentic systems. However, most of the literature on this topic is from the AI standpoint and lacks the system-security perspective and guarantees. In this work, we begin bridging this gap and present an analysis through the lens of classic cybersecurity research. Specifically, motivated by decades of progress in this domain, we identify short- and long-term research problems in agentic AI safety by examining end-to-end security properties of entire systems, rather than standalone AI models running in isolation. Our key goal is to examine where research challenges arise when applying traditional security principles in the context of AI agents and, as a secondary goal, distill these ideas for AI practitioners. Furthermore, we extensively cover 11 case studies of real-world attacks on agentic systems, as well as define a series of new research problems that are specific to this important domain.

cs.CR↗

Can We Infer Confidential Properties of Training Data from LLMs?

Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datasets often have sensitive and confidential dataset-level properties -- such as patient demographics or disease prevalence -- that are not intended to be revealed. While prior work has studied property inference attacks on discriminative models (e.g., image classification models) and generative models (e.g., GANs for image data), it remains unclear if such attacks transfer to LLMs. In this work, we introduce PropInfer, a benchmark task for evaluating property inference in LLMs under two fine-tuning paradigms: question-answering and chat-completion. Built on the ChatDoctor dataset, our benchmark includes a range of property types and task configurations. We further propose two tailored attacks: a prompt-based generation attack and a shadow-model attack leveraging word frequency signals. Empirical evaluations across multiple pretrained LLMs show the success of our attacks, revealing a previously unrecognized vulnerability in LLMs.

cs.LG↗

Privacy Blur: Quantifying Privacy and Utility for Image Data Release

Image data collected in the wild often contains private information such as faces and license plates, and responsible data release must ensure that this information stays hidden. At the same time, released data should retain its usefulness for model-training. The standard method for private information obfuscation in images is Gaussian blurring. In this work, we show that practical implementations of Gaussian blurring are reversible enough to break privacy. We then take a closer look at the privacy-utility tradeoffs offered by three other obfuscation algorithms -- pixelization, pixelization and noise addition (DP-Pix), and cropping. Privacy is evaluated by reversal and discrimination attacks, while utility by the quality of the learnt representations when the model is trained on data with obfuscated faces. We show that the most popular industry-standard method, Gaussian blur is the least private of the four -- being susceptible to reversal attacks in its practical low-precision implementations. In contrast, pixelization and pixelization plus noise addition, when used at the right level of granularity, offer both privacy and utility for a number of computer vision tasks. We make our proposed methods together with suggested parameters available in a software package called Privacy Blur.

cs.LG↗

CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate contexts. We present CIMemories, a benchmark for evaluating whether LLMs appropriately control information flow from memory based on task context. CIMemories uses synthetic user profiles with over 100 attributes per user, paired with diverse task contexts in which each attribute may be essential for some tasks but inappropriate for others. Our evaluation reveals that frontier models exhibit up to 69% attribute-level violations (leaking information inappropriately), with lower violation rates often coming at the cost of task utility. Violations accumulate across both tasks and runs: as usage increases from 1 to 40 tasks, GPT-5's violations rise from 0.1% to 9.6%, reaching 25.1% when the same prompt is executed 5 times, revealing arbitrary and unstable behavior in which models leak different attributes for identical prompts. Privacy-conscious prompting does not solve this - models overgeneralize, sharing everything or nothing rather than making nuanced, context-dependent decisions. These findings reveal fundamental limitations that require contextually aware reasoning capabilities, not just better prompting or scaling.

cs.CR↗

Evaluating Deep Unlearning in Large Language Models

Machine unlearning has emerged as an important component in developing safe and trustworthy models. Prior work on fact unlearning in LLMs has mostly focused on removing a specified target fact robustly, but often overlooks its deductive connections to other knowledge. We propose a new setting for fact unlearning, deep unlearning, where the goal is not only to remove a target fact but also to prevent it from being deduced via retained knowledge in the LLM and logical reasoning. We propose three novel metrics: Success-DU and Recall to measure unlearning efficacy, and Accuracy to measure the remainder model utility. To benchmark this setting, we leverage both (1) an existing real-world knowledge dataset, MQuAKE, that provides one-step deduction instances, and (2) newly construct a novel semi-synthetic dataset, Eval-DU, that allows multiple steps of realistic deductions among synthetic facts. Experiments reveal that current methods struggle with deep unlearning: they either fail to deeply unlearn, or excessively remove unrelated facts. Our results suggest that targeted algorithms may have to be developed for robust/deep fact unlearning in LLMs.

cs.CL↗

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy

With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose, retrieval-augmented generation (RAG) is particularly effective -- it assists LLMs by directly providing relevant information from the external knowledge sources. However, without extra privacy safeguards, RAG outputs risk leaking sensitive information from the external data source. In this work, we explore RAG under differential privacy (DP), a formal guarantee of data privacy. The main challenge with differentially private RAG is how to generate long accurate answers within a moderate privacy budget. We address this by proposing an algorithm that smartly spends privacy budget only for the tokens that require the sensitive information and uses the non-private LLM for other tokens. Our extensive empirical evaluations reveal that our algorithm outperforms the non-RAG baseline under a reasonable privacy budget of $ε\approx 10$ across different models and datasets.

cs.CR↗

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential dependencies and the non-deterministic nature of knowledge within LLMs. Consequently, facts presumed forgotten may persist implicitly through correlated information. To address these challenges, we propose a knowledge unlearning evaluation framework that more accurately captures the implicit structure of real-world knowledge by representing relevant factual contexts as knowledge graphs with associated confidence scores. We further develop an inference-based evaluation protocol leveraging powerful LLMs as judges; these judges reason over the extracted knowledge subgraph to determine unlearning success. Our LLM judges utilize carefully designed prompts and are calibrated against human evaluations to ensure their trustworthiness and stability. Extensive experiments on our newly constructed benchmark demonstrate that our framework provides a more realistic and rigorous assessment of unlearning performance. Moreover, our findings reveal that current evaluation strategies tend to overestimate unlearning effectiveness. Our code is publicly available at https://github.com/Graph-COM/Knowledge_Unlearning.git.

cs.CL↗