REVIEW 3 cited by
Improving the Adversarial Robustness of NLP Models by Information Bottleneck
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Existing studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manipulated by adversaries to fool NLP models. In this study, we explore the feasibility of capturing task-specific robust features, while eliminating the non-robust ones by using the information bottleneck theory. Through extensive experiments, we show that the models trained with our information bottleneck-based method are able to achieve a significant improvement in robust accuracy, exceeding performances of all the previously reported defense methods while suffering almost no performance drop in clean accuracy on SST-2, AGNEWS and IMDB datasets.
Forward citations
Cited by 3 Pith papers
-
VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
VIBE selects task-relevant video summaries by combining a grounding score (video-text alignment) and a utility score (task informativeness), improving human accuracy by up to 61% in user studies.
-
Evaluation of Adversarial Robustness in Arabic Language Models
Arabic BERT-family sentiment models lose up to 92% accuracy under diacritics and 58% under conjunction attacks; paraphrase attacks cut accuracy by 76% on average, and adversarial training only partially helps.
-
A Survey on Data Security in Large Language Models
A survey of data security risks in LLMs that organizes threats, defenses, and evaluation datasets, with notable factual errors in its tables.
Discussion (0). Continue with ORCID to comment.