Search Results for author:
Found 4 papers, 0 papers with code
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks
Previous works on word-level attacks widely use word importance ranking (WIR) methods and complex search methods, including greedy search and heuristic algorithms, to find optimal substitutions.
Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training
We show that the pathological inconsistency is caused by the representation collapse issue, which means that the representation of the sentences with tokens in different saliency reduced is somehow collapsed, and thus the important words cannot be distinguished from unimportant words in terms of model confidence changing.
Website fingerprinting on early QUIC traffic
Extensive experiments show that, in the early traffic scenario, GQUIC is the most vulnerable to WFP attacks among GQUIC, IQUIC, and HTTPS, while IQUIC is more vulnerable than HTTPS, but the vulnerability of the three protocols is similar in the normal full traffic scenario.
