arXiv Machine Learning October 3, 2026 By Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik, Aron Laszka

SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples

Read the original on arXiv Machine Learning →

SAGE is a defense against clean‑label data poisoning that relies on a very small set of verified examples—both clean and poisoned—rather than a large clean set. It trains a generic feature extractor on a separate dataset and then uses a non‑parametric, similarity‑weighted prediction to flag poisoned training examples. Experiments on standard benchmarks show that even a handful of verified poisoned examples give a substantial advantage, and that the distribution of verified clean examples across classes is more important than their sheer number.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Sep 15

Are Targeted Data Poisoning Attacks as Effective as We Think?

arXiv:2509.06896v3 Announce Type: replace Abstract: Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evalu...

By William Xu, Chenyu Zhang, Yihan Wang, Matthew Y. R. Yang, Zuoqiu Liu, Yaoliang Yu, Gautam Kamath, Yiwei Lu

Hugging Face Trending Papers

Jul 7

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples.

arXiv Machine Learning

Jul 8

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

arXiv:2607. 05748v1 Announce Type: new Abstract: The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning.

By Qi Zhao, Christian Wressnegger

arXiv Machine Learning

Sep 1

Trust Under Siege: Label Spoofing Attacks against Machine Learning for Android Malware Detection

arXiv:2503.11841v2 Announce Type: replace-cross Abstract: Machine Learning (ML) malware detectors rely heavily on crowd-sourced AntiVirus (AV) labels, with platforms like VirusTotal serving as truste...

By Tianwei Lan, Luca Demetrio, Farid Nait-Abdesselam, Yufei Han, Simone Aonzo

rag benchmarks

arXiv AI

Jun 30

Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

arXiv:2606. 28953v1 Announce Type: cross Abstract: Poisoning attacks entail attackers intentionally tampering with training data.

By Thomas Thebaud, Sonal Joshi, Henry Li, Martin Sustek, Jesus Villalba, Sanjeev Khudanpur, Najim Dehak

efficiency

arXiv Machine Learning

Aug 4

Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors

arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.

By Niraj Kumar, Harsh Kasyap

rag benchmarks safety

One email a morning, machine-written

Related stories

Are Targeted Data Poisoning Attacks as Effective as We Think?

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

Trust Under Siege: Label Spoofing Attacks against Machine Learning for Android Malware Detection

Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors