When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers
RAMP: Reversing Adversarial Perturbations to Strengthen Clean-Label Backdoor Attacks against Malware Detectors
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
A GAN-Based Framework for Robust DDoS Attack Detection
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
1
Implementing a White-Box Undetectable Backdoor for Random Fourier Features
Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness
1