Hugging Face Trending Papers

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

Read the original on Hugging Face Trending Papers →

Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few samples convey the trigger--target association, making poison-sample selection critical.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

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 30

Lilith: Backdoor Generalization under Training-Inference Trigger Shift

arXiv:2607. 26099v1 Announce Type: cross Abstract: Machine-learning services increasingly rely on public data, third-party providers, and outsourced training, creating opportunities for data-poisoning attacks that implant persistent malicious behavior while preserving benign utility.

By Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuan Su, Tianyu Du, Yuwen Pu, Jianhai Chen, Jinbao Li, Shouling Ji