arXiv subjects

Matthew Jagielski

Publications and source records attributed to Matthew Jagielski.

At least 19 recordsLinked to original sources

arXiv2026

Agentic Backdoors via Pretraining Poisoning

Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraining data. We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attacker-chosen commands on the user's machine. To measure the threat end to end, we pretrain Qwen3 models from scratch at sizes 0.6B, 1.7B, and 4B, and then post-train each into a CLI agent using a clean pipeline. Poisoning only 0.1% of the pretraining corpus with our new poison design implants the backdoor: the deployed agent executes the malicious command when the trigger is present while behaving normally on clean inputs. The attack success rate (ASR) increases with model scale, with the 4B model reaching roughly 92% ASR at a 0.1% poison rate and staying positive even when the poisoning rate drops to 0.0005%. Our code is available at https://github.com/safety-research/agentic-backdoor.

cs.CR↗

arXiv2026

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML engineering. We introduce Agent4Sci, a long-horizon testbed for measuring how far today's agents can improve the published best models on scientific ML benchmarks, spanning 20 benchmarks across 11 domains. Rather than ranking agents on a leaderboard, Agent4Sci asks what kinds of progress agents can make on these tasks under in-the-wild conditions, and where they fall short. Empirically, today's frontier agents advance the published best on every benchmark, with Claude Opus reaching 10.4% mean relative improvement and no run flagged for academic misconduct. These gains, however, come almost entirely from a bag of ML-engineering tricks rather than research-level insight. Trajectory analysis surfaces three recurring limitations in this setting: novelty miscalibration, resource under-utilization, and rapid collapse into local engineering sweeps. Lightweight plug-in skills for research ideation, experiment management, and scheduled checklists raise Claude Opus from 10.4% to 20.1% and Codex from 4.4% to 8.1%, while yielding more diverse, domain-relevant interventions. Agent4Sci gives the community a way to track and push frontier agents from ML engineering toward domain insight on real-world ML-for-science problems. Code and data are available on GitHub (https://github.com/maszhongming/agent4sci) and Hugging Face (https://huggingface.co/datasets/MingZhong/agent4sci).

cs.AI↗

arXiv2026

The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark

AI agents are rapidly improving in cybersecurity when source code is available, yet much of the software most consequential to security, including malware, firmware, and proprietary applications, exists only as binaries. Analyzing such software requires reverse engineering (RE): recovering program semantics before analysis can proceed. Evaluating agentic RE poses a fundamental challenge: realistic benchmark instances must (1) be absent from LLMs' training data to prevent shortcuts by memorization, and (2) reflect the scale and anti-analysis protections of real-world binaries. We introduce SRE-Bench, the first realistic, contamination-free RE benchmark. Built from scratch by RE experts with over 5,000 expert hours, SRE-Bench comprises 19 private, real-world-scale programs averaging 16.9K lines of code. We further developed 44 in-house anti-analysis mechanisms, yielding 262 binary instances and 1,572 deterministically graded tasks. We evaluated 13 agentic settings across 11 models: eight in public-facing settings and five in internal unconstrained settings with cyber safeguards disabled and no budget cap. Realistic RE remains challenging for frontier agents: GPT-5.6-Sol and Claude-Fable-5.1, despite strong source-code security capabilities, fully solve only 31.5% and 26.9% of graded instances, suggesting that success in source-code security does not translate into effective binary analysis. Without a budget cap and safety guard, GPT-6-Astra achieves a near-perfect pass@4 score, yet reliably identifying the correct candidate remains difficult. Agents are largely insensitive to compiler optimization and static linking, and ablations confirm that both contamination control and realistic scale are essential to understanding agents' RE capability. These findings highlight RE as a distinct frontier for agentic cybersecurity and establish SRE-Bench as a rigorous testbed for measuring progress.

cs.CR↗

arXiv2026

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate pool. We show that this can severely underestimate worst-case vulnerability: across three LLaMA-3-8B backdoor settings, holding the model, clean data, and poison count fixed, attack success ranges from 3% to 80% depending only on which poison set is chosen. We formalize poison selection as oracle-budgeted set optimization and introduce SAILS (Set-level Audit-Informed Iterative Learned Selection), which learns a set scorer from a few hundred finetune-and-evaluate runs, ranks millions of candidate sets, and audits only a small shortlist. SAILS improves held-out attack success by 30 percentage points on average over the strongest influence baselines, transfers from small-scale to full-scale finetuning, and extends to code-generation, agentic, and API-only backdoors.

cs.LG↗

arXiv2026

CryptanalysisBench: Can LLMs do Cryptanalysis?

Cryptanalysis - the task of finding attacks against cryptographic schemes - sits at the intersection of mathematical reasoning and cybersecurity, two areas where LLMs have advanced fastest. Cryptanalysis represents both a clean testbed for frontier reasoning (as practical attacks can be automatically verified) and a domain with unusually high stakes, since the primitives under study underpin our digital security. In this paper we ask whether LLMs can do cryptanalysis, and find that the answer is increasingly yes. We introduce CryptanalysisBench, 191 tasks across six families of cryptographic primitives (block ciphers, hash functions, etc.) drawn primarily from four NIST standardization competitions. Our benchmark consists of three tiers: (i) primitives with known practical breaks; (ii) primitives with no known practical break, evaluated both at full strength and as scaled-down variants; and (iii) a challenge set of production primitives at the frontier of cryptanalysis. Five frontier models (Claude Opus 4.8, Sonnet 5, Mythos 5, GPT 5.5, and the open-weights GLM 5.2) break 65%-86% of Tier 1 schemes, 6-12 Tier-2 schemes at full strength, and 24-61 across all scaled-down variants. Beyond deriving known results, models produce novel cryptanalysis, such as a key-recovery attack that exploits a design flaw in the SpoC AEAD and an error in KINDI's published CCA-security proof, both to the best of our knowledge not previously known. We release CryptanalysisBench as a tool to help track if (or when) AI cryptanalysis becomes a serious factor and as a scaffold for stress-testing candidate schemes before deployment. The attacks that the benchmark already surfaces are an early snapshot of a fast-moving frontier that may soon match, and in places exceed, the published state of the art.

cs.CR↗

arXiv2026

The 2026 Singapore Consensus on Global AI Safety Research Priorities

Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential to embracing AI with confidence. The 2026 Singapore Consensus is an outcome of the second International Scientific Exchange on AI Safety, bringing together over 100 contributors spanning 13 countries from frontier developers, government safety institutes, academia, and civil society. Building on the 2025 report, it presents a global understanding of technical AI safety research problems of top priority, now with a dedicated focus on societal resilience and on managing the risks of increasingly autonomous AI agents.

cs.CY↗

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

TabPATE: Differentially Private Tabular In-Context Learning Without Public Data

Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We first show that even basic membership inference attacks succeed against tabular ICL, motivating formal privacy protection. We then introduce TabPATE, a differentially private PATE-style defense for tabular ICL that does not require public in-distribution data. TabPATE partitions the private context across teacher models, privately aggregates their labels on synthetic tabular queries, and releases the resulting labeled queries as a student context. Because tabular features are bounded and relatively low-dimensional, useful queries can be generated from feature ranges alone or from lightly privatized marginals. Across tabular benchmarks, TabPATE preserves competitive utility while reducing membership inference to near-random success, providing a practical path to private tabular ICL without public data.

cs.LG↗

arXiv2026

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning

In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as a solution for private machine learning: rather than training directly on sensitive data, which is known to leak information through model predictions, the private data is used only to guide the selection of useful public data. The resulting model is then trained solely on curated public data. It is tempting to assume that such a model is privacy-preserving because it has never seen the private data. Yet, we show that without further protection, curation pipelines can still leak private information. Specifically, we introduce novel attacks against popular curation methods, targeting every major step: the computation of curation scores, the selection of the curated subset, and the final trained model. We demonstrate that each stage reveals information about the private dataset and that even models trained exclusively on curated public data leak membership information about the private data that guided curation. These findings highlight the previously overlooked inherent privacy risks of data curation and show that privacy assessment must extend beyond the training procedure to include the data selection process. Our differentially private adaptations of curation methods effectively mitigate leakage, indicating that formal privacy guarantees for curation are a promising direction.

cs.LG↗

arXiv2026

SoK: Data Minimization in Machine Learning

Data minimization (DM) describes the principle of collecting only the data strictly necessary for a given task. It is a foundational principle across major data protection regulations like GDPR and CPRA. Violations of this principle have substantial real-world consequences, with regulatory actions resulting in fines reaching hundreds of millions of dollars. Notably, the relevance of data minimization is particularly pronounced in machine learning (ML) applications, which typically rely on large datasets, resulting in an emerging research area known as Data Minimization in Machine Learning (DMML). At the same time, existing work on other ML privacy and security topics often addresses concerns relevant to DMML without explicitly acknowledging the connection. This disconnect leads to confusion among practitioners, complicating their efforts to implement DM principles and interpret the terminology, metrics, and evaluation criteria used across different research communities. To address this gap, we present the first systematization of knowledge (SoK) for DMML. We introduce a general framework for DMML, encompassing a unified data pipeline, adversarial models, and points of minimization. This framework allows us to systematically review data minimization literature as well as DM-adjacent methodologies whose link to DM was often overlooked. Our structured overview is designed to help practitioners and researchers effectively adopt and apply DM principles in ML, by helping them identify relevant techniques and understand underlying assumptions and trade-offs through a DM-centric lens.

cs.LG↗

arXiv2026

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to fine-tune pre-trained models using CoT datasets from public repositories like HuggingFace, which creates new attack vectors targeting the reasoning traces themselves. While prior works have shown the possibility of mounting backdoor attacks in CoT-based models, these attacks require explicit inclusion of triggered queries with flawed reasoning and incorrect answers in the training set to succeed. Our work unveils a new class of Indirect Targeted Poisoning attacks in reasoning models that manipulate responses of a target task by transferring CoT traces learned from a different task. Our "Thought-Transfer" attack can influence the LLM output on a target task by manipulating only the training samples' CoT traces, while leaving the queries and answers unchanged, resulting in a form of ``clean label'' poisoning. Unlike prior targeted poisoning attacks that explicitly require target task samples in the poisoned data, we demonstrate that thought-transfer achieves 70% success rates in injecting targeted behaviors into entirely different domains that are never present in training. Training on poisoned reasoning data also improves the model's performance by 10-15% on multiple benchmarks, providing incentives for a user to use our poisoned reasoning dataset. Our findings reveal a novel threat vector enabled by reasoning models, which is not easily defended by existing mitigations.

cs.CR↗

arXiv2026

Exploring the limits of strong membership inference attacks on large language models

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on weaker attacks that avoid training references (e.g., fine-tuning attacks), or on stronger attacks applied to small models and datasets. However, weaker attacks have been shown to be brittle and insights from strong attacks in simplified settings do not translate to today's LLMs. These challenges prompt an important question: are the limitations observed in prior work due to attack design choices, or are MIAs fundamentally ineffective on LLMs? We address this question by scaling LiRA--one of the strongest MIAs--to GPT-2 architectures ranging from 10M to 1B parameters, training references on over 20B tokens from the C4 dataset. Our results advance the understanding of MIAs on LLMs in four key ways. While (1) strong MIAs can succeed on pre-trained LLMs, (2) their effectiveness, remains limited (e.g., AUC<0.7) in practical settings. (3) Even when strong MIAs achieve better-than-random AUC, aggregate metrics can conceal substantial per-sample MIA decision instability: due to training randomness, many decisions are so unstable that they are statistically indistinguishable from a coin flip. Finally, (4) the relationship between MIA success and related LLM privacy metrics is not as straightforward as prior work has suggested.

cs.CR↗

arXiv2025

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific information from a generative-AI model's parameters, e.g., a particular individual's personal data or the inclusion of copyrighted content in the model's training data. Unlearning is also proposed as a way to prevent a model from generating targeted types of information in its outputs, e.g., generations that closely resemble a particular individual's data or reflect the concept of "Spiderman." Both of these goals--the targeted removal of information from a model and the targeted suppression of information from a model's outputs--present various technical and substantive challenges. We provide a framework for ML researchers and policymakers to think rigorously about these challenges, identifying several mismatches between the goals of unlearning and feasible implementations. These mismatches explain why unlearning is not a general-purpose solution for circumscribing generative-AI model behavior in service of broader positive impact.

cs.LG↗

arXiv2025

Extracting alignment data in open models

In this work, we show that it is possible to extract significant amounts of alignment training data from a post-trained model -- useful to steer the model to improve certain capabilities such as long-context reasoning, safety, instruction following, and maths. While the majority of related work on memorisation has focused on measuring success of training data extraction through string matching, we argue that embedding models are better suited for our specific goals. Distances measured through a high quality embedding model can identify semantic similarities between strings that a different metric such as edit distance will struggle to capture. In fact, in our investigation, approximate string matching would have severely undercounted (by a conservative estimate of $10\times$) the amount of data that can be extracted due to trivial artifacts that deflate the metric. Interestingly, we find that models readily regurgitate training data that was used in post-training phases such as SFT or RL. We show that this data can be then used to train a base model, recovering a meaningful amount of the original performance. We believe our work exposes a possibly overlooked risk towards extracting alignment data. Finally, our work opens up an interesting discussion on the downstream effects of distillation practices: since models seem to be regurgitating aspects of their training set, distillation can therefore be thought of as indirectly training on the model's original dataset.

cs.AI↗

arXiv2025

Cascading Adversarial Bias from Injection to Distillation in Language Models

Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper investigates vulnerability of distilled models to adversarial injection of biased content during training. We demonstrate that adversaries can inject subtle biases into teacher models through minimal data poisoning, which propagates to student models and becomes significantly amplified. We propose two propagation modes: Untargeted Propagation, where bias affects multiple tasks, and Targeted Propagation, focusing on specific tasks while maintaining normal behavior elsewhere. With only 25 poisoned samples (0.25% poisoning rate), student models generate biased responses 76.9% of the time in targeted scenarios - higher than 69.4% in teacher models. For untargeted propagation, adversarial bias appears 6x-29x more frequently in student models on unseen tasks. We validate findings across six bias types (targeted advertisements, phishing links, narrative manipulations, insecure coding practices), various distillation methods, and different modalities spanning text and code generation. Our evaluation reveals shortcomings in current defenses - perplexity filtering, bias detection systems, and LLM-based autorater frameworks - against these attacks. Results expose significant security vulnerabilities in distilled models, highlighting need for specialized safeguards. We propose practical design principles for building effective adversarial bias mitigation strategies.

cs.LG↗

arXiv2025

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation

Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant knowledge sources. It is particularly useful in chatbot applications, allowing developers to customize LLM output without expensive retraining. Despite their significant utility in various applications, RAG systems present new security risks. In this work, we propose a novel attack that allows an adversary to inject a single malicious document into a RAG system's knowledge base, and mount a backdoor poisoning attack. We design Phantom, a general two-stage optimization framework against RAG systems, that crafts a malicious poisoned document leading to an integrity violation in the model's output. First, the document is constructed to be retrieved only when a specific naturally occurring trigger sequence of tokens appears in the victim's queries. Second, the document is further optimized with crafted adversarial text that induces various adversarial objectives on the LLM output, including refusal to answer, reputation damage, privacy violations, and harmful behaviors.We demonstrate our attacks on multiple open-source LLM architectures, including Gemma, Vicuna, and Llama, and show that they transfer to closed-source models such as GPT-3.5 Turbo and GPT-4. Finally, we successfully demonstrate our attack on an end-to-end black-box production RAG system: NVIDIA's "Chat with RTX''.

cs.CR↗

arXiv2025

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training

Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. Beyond this, PII may be added or removed from training datasets due to evolving dataset curation techniques, because they were newly scraped for retraining, or because they were included in a new downstream fine-tuning stage. We find that the amount and ease of PII memorization is a dynamic property of a model that evolves throughout training pipelines and depends on commonly altered design choices. We characterize three such novel phenomena: (1) similar-appearing PII seen later in training can elicit memorization of earlier-seen sequences in what we call assisted memorization, and this is a significant factor (in our settings, up to 1/3); (2) adding PII can increase memorization of other PII significantly (in our settings, as much as $\approx\!7.5\times$); and (3) removing PII can lead to other PII being memorized. Model creators should consider these first- and second-order privacy risks when training models to avoid the risk of new PII regurgitation.

cs.CL↗

arXiv2025

Black-Box Privacy Attacks on Shared Representations in Multitask Learning

Multitask learning (MTL) has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, to solve them simultaneously while minimizing data sharing across users and organizations. MTL typically accomplishes this goal by learning a shared representation that captures common structure among the tasks by embedding data from all tasks into a common feature space. Despite being designed to be the smallest unit of shared information necessary to effectively learn patterns across multiple tasks, these shared representations can inadvertently leak sensitive information about the particular tasks they were trained on. In this work, we investigate what information is revealed by the shared representations through the lens of inference attacks. Towards this, we propose a novel, black-box task-inference threat model where the adversary, given the embedding vectors produced by querying the shared representation on samples from a particular task, aims to determine whether that task was present when training the shared representation. We develop efficient, purely black-box attacks on machine learning models that exploit the dependencies between embeddings from the same task without requiring shadow models or labeled reference data. We evaluate our attacks across vision and language domains for multiple use cases of MTL and demonstrate that even with access only to fresh task samples rather than training data, a black-box adversary can successfully infer a task's inclusion in training. To complement our experiments, we provide theoretical analysis of a simplified learning setting and show a strict separation between adversaries with training samples and fresh samples from the target task's distribution.

cs.LG↗