← Back to all news
arXiv AI By Longtian Wang, Zhengyu Zhao, Chenhao Lin, Le Yang, Shiwei Wang, Yuhan Zhi, Xiaofei Xie, Chao Shen

Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift

Read the original on arXiv AI →

The paper introduces DistScan, a backdoor detection framework for object detection models that identifies malicious behavior by detecting shifts in the pre‑NMS prediction class distribution relative to training class frequencies. DistScan operates on clean validation data, requiring no access to model weights, trigger knowledge, or additional training, and it aggregates intermediate predictions to flag backdoored models. Experiments on MS‑COCO and PASCAL VOC across two architectures and three scene‑level attack scenarios show that DistScan outperforms existing methods, improving average detection accuracy by 27.32 percentage points over the best baseline.

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 AI.

Related stories

arXiv AI
5d ago

STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning

The paper introduces STAIN-FL, a stealthy backdoor attack framework for federated video anomaly detection that uses natural surveillance conditions—such as low light, indoor settings, and crowd density—as contextual triggers. STAIN-FL manipulates anomaly labels and masks gradients to keep clean accuracy low while inducing trigger‑conditioned misclassification. Experiments on UCF‑Crime with I3D features show that sparse attacks remain undetectable, drop clean accuracy by less than 2%, yet achieve over 50% backdoor accuracy for hundreds of rounds under FedAvg and FedProx.

By Ashlinder Kaur, Purnima Murali Mohan, Zengxiang Li, Tram Truong-Huu
robotics
More like this →
arXiv AI
Jun 8

Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs

arXiv:2601. 12359v1 Announce Type: cross Abstract: Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful or unintended outputs.

By Anirudh Sekar, Mrinal Agarwal, Rachel Sharma, Akitsugu Tanaka, Jasmine Zhang, Arjun Damerla, Kevin Zhu
llmsragbenchmarkssafety
More like this →