Skip to content

TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement

Sep 2026 · 0 citations · 90 references
Computer Science

TL;DR

This work introduces TraceGuard, an adaptive rank-based filtering method that uses agreement among complementary feature rankings to identify suspicious examples and refines the selected set through shared patterns and adapts the removal threshold to each corpus without knowing the attack or poison rate.

Abstract

Multimodal training relies on image-text corpora collected from external sources, creating opportunities for attackers to poison the data. Stealthy attacks can preserve plausible image-text pairs while concealing the differences used by detectors, so apparently clean data can still redirect the trained model. We therefore ask which properties a poison set must preserve for the attack to remain effective. A small poison set must still exert enough collective influence during training to induce the attacker's target behavior. We analyze this influence in terms of how often an attack pattern occurs and how strongly the examples carrying it jointly affect the model. This analysis motivates six corpus-level features that examine cross-modal neighborhoods, recurring text, and changes after text-span erasure without training the victim model. We introduce TraceGuard, an adaptive rank-based filtering method that uses agreement among complementary feature rankings to identify suspicious examples. It refines the selected set through shared patterns and adapts the removal threshold to each corpus without knowing the attack or poison rate. Across 19 attack configurations spanning image-text learning, generative vision-language model fine-tuning, and encoder-transfer tests, TraceGuard removes an average of 98.4% of poisoned examples and 5.4% of clean examples. After training on the filtered corpora, the residual attack metric is at most 1% in 13 configurations. Matched-removal controls and ablations support the contributions of sample selection and adaptive removal. Stress tests also identify detection failures under adaptive attacks and unnecessary removal on poison-free corpora.

View source

Similar papers

#small language model Review Sep 2026

Detecting and Localizing Segment-Level Poisoning in Multi-Source LLM-Agent Inputs

ActProbe, an internal-state-based framework for detecting and localizing poisoned segments in multi-source LLM inputs, is proposed and remains effective against defense-aware adaptive attacks and can protect black-box APIs through surrogate-based poisoned-segment removal.

Xue Tan, Chang-Hui Wang, Sanrui Yang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Fingerprinting Multimodal Large Language Models

While multimodal large language models (MLLMs) enable a wide range of image-text reasoning tasks, recent incidents indicate that they are vulnerable to illicit deployment and unauthorized distillation. Existing solutions for model provenance are typically confounded by shared language backbones in MLLMs and struggle to...

Chao Huang, Meng Tong, Kejiang Chen · 0 citations
Preprint Aug 2026

Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks

DFCS is proposed, a training-free, trigger-agnostic method that clusters fixed pretrained features into one region per poisoning slot and selects the centroid-nearest sample from each region and supports distributional feature coverage as an effective selection principle for low-budget dirty-label backdoor attacks.

Yi Yang, Xiaoke Chen, Jin-Yang Huang et al. · 0 citations
Book Open access Sep 2026

MaskPoison: Intent-Guided Poisoning Attacks on Sequential Recommendation via Masked Discrete Diffusion

Sequential recommendation (SR) systems are widely deployed across modern online platforms, and have been shown to be vulnerable to poisoning attacks. Such attacks inject fabricated user sequences into training data to promote target items. Existing methods achieve stealthiness by enforcing surface-level similarity to g...

Hang-Chang Zhou, Hong-Xu Ma, Hui Fang et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

Microsoft Research Blog Nov 3, 2026

Learn the rules: The hacker mindset

Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.