REVIEW 4 cited by
Assessing Adversarial Robustness of Large Language Models: An Empirical Study
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
Signed reviews
read the original abstract
Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in leading open-source LLMs, including Llama, OPT, and T5. We assess the impact of model size, structure, and fine-tuning strategies on their resistance to adversarial perturbations. Our comprehensive evaluation across five diverse text classification tasks establishes a new benchmark for LLM robustness. The findings of this study have far-reaching implications for the reliable deployment of LLMs in real-world applications and contribute to the advancement of trustworthy AI systems.
Forward citations
Cited by 4 Pith papers
-
Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol
This position paper classifies testing methods for LLM applications into three layers and proposes AICL, a structured protocol for testable agent communication; neither the framework nor the protocol is empirically validated.
-
Adversarial Attack on Large Language Models using Exponentiated Gradient Descent
Exponentiated gradient descent over relaxed one-hot token encodings finds adversarial suffixes that jailbreak several open-source LLMs with higher success rate and lower runtime than GCG, PGD, and SoftPromptThreats.
-
Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach
A Jacobian-magnitude regularization called GBM improves empirical robustness of CNN/LSTM/S4 text classifiers to synonym-substitution attacks, but the claimed certified robustness is not delivered.
-
On Adversarial Robustness of Language Models in Transfer Learning
Sequential fine-tuning across related bias-detection tasks tends to raise adversarial attack success rates, but the size-resilience pattern the paper highlights is not borne out by its own data.
Discussion (0). Continue with ORCID to comment.