2 papers
cs.CR2026
Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
Yudong Gao, Linghan Chen, Wenhan Wu +5
Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a…
cs.CL2026
Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution
Yijun Liao, Fanwei Liang
When a context asserts two values for one fact, a model commits to a cue -- recency, repetition, position -- but natural data rarely makes these disagree, so behavior cannot reveal…