This paper proposes optimal testing strategies which can still recover needed test results even if there are cheaters polluting the results, and determines the optimal testing strategies using a dynamic programming method.
Abstract
In applications, it is often required to test objects or people to determine their qualities in terms of certain metrics. However, besides being naturally noisy, the test results can be corrupted by adversarial behaviors of objects or people being tested (test takers). For example, dishonest test takers can cheat in the exams to distort the test results. With the development of AI technologies, such distortions driven by cheating using AI technologies are becoming more commonplace and severe. In this paper, we propose optimal testing strategies which can still recover needed test results even if there are cheaters polluting the results. The proposed testing strategies will optimally re-test selected group of test takers using different testing security measures. We determine the optimal testing strategies using a dynamic programming method.
This work presents a two-phase evaluation of ten Llama variants using the OWASP Top 10 for LLM Applications, and applies nine encoding obfuscations to the same prompts, which fully bypasses all text-only models.
Nourin Shahin, Izzat Alsmadi· Practice and Experience in A...· 0 citations
This paper systematically synthesizes 27 studies of attacks against MGTD and the available evidence on corresponding defenses, categorizing existing research into four major types of evasion strategies: watermark attacks, paraphrasing attacks, prompt-based attacks, and adversarial-text attacks, and summarizes the avail...
De-Yu Meng, Tad Gonsalves· Neural Networks· 0 citations
No method reliably surfaces every backdoor, but a broadly jailbreakable model is itself anomalous, a useful signal even when the exact trigger is not recovered, allowing defenders to filter jailbreaks.
A. Hughes, N. Xing, Collin Francel et al.· arXiv.org· 0 citations
Dueling bandit algorithms excel in learning from pairwise comparisons, offering robust performance guarantees in benign environments. However, recent evidence suggests that even state-of-the-art methods can be highly susceptible to adversarial manipulation. In this work, we introduce and analyze a post-action attack mo...
Mo Lyu, Chen-Ye Yang, Guan-Lin Liu et al.· IEEE Transactions on Signal...· 0 citations
ExE-Bench assesses performance, temporal and adversarial robustness, and computational overhead, aggregating them into a single score for direct and fair model comparison, and highlights how evaluations conducted only after deployment are suboptimal and unable to provide a complete picture of their performance.
Andrea Ponte, Daniel Gibert, M. Kozák et al.· arXiv.org· 0 citations
Under the single-shot, raw-bytecode-only protocol, current LLMs are not reliable standalone forensic tools, and their robustness has not been systematically tested against contracts adversarially designed to mislead analysis.
