paper-with-me

Papers

DelBugV: Delta-Debugging Neural Network Verifiers

2023-05-29 · Raya Elsaleh, Guy Katz

Deep neural networks (DNNs) are becoming a key component in diverse systems across the board. However, despite their success, they often err miserably; and this has triggered significant interest in formally verifying them. Unfortunately, DNN verifiers are intricate tools, and are themselves susceptible to soundness bugs. Due to the complexity of DNN verifiers, as well as the sizes of the DNNs being verified, debugging such errors is a daunting task. Here, we present a novel tool, named DelBugV, that uses automated delta debugging techniques on DNN verifiers. Given a malfunctioning DNN verifier and a correct verifier as a point of reference (or, in some cases, just a single, malfunctioning verifier), DelBugV can produce much simpler DNN verification instances that still trigger undesired behavior -- greatly facilitating the task of debugging the faulty verifier. Our tool is modular and extensible, and can easily be enhanced with additional network simplification methods and strategies. For evaluation purposes, we ran DelBugV on 4 DNN verification engines, which were observed to produce incorrect results at the 2021 neural network verification competition (VNN-COMP'21). We were able to simplify many of the verification queries that trigger these faulty behaviors, by as much as 99%. We regard our work as a step towards the ultimate goal of producing reliable and trustworthy DNN-based software.

📄 PDF Abstract BibTeX arXiv:2305.18558

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair

2026-06-02 · Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang 외 arxiv

While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (De…

DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

2026-02-22 · Krishna Khadka, Yu Lei, Raghu N. Kacker, D. Richard Kuhn arxiv

We introduce a gradient-free framework for identifying minimal, sufficient, and decision-preserving explanations in vision models by isolating the smallest subset of representational units whose joint activation preserve…

Can ChatGPT support software verification?

2023-11-04 · Christian Janßen, Cedric Richter, Heike Wehrheim

Large language models have become increasingly effective in software engineering tasks such as code generation, debugging and repair. Language models like ChatGPT can not only generate code, but also explain its inner wo…

Code Generationvalid

Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step

2024-02-25 · Li Zhong, Zilong Wang, Jingbo Shang

Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the gener…

Code GenerationHumanEvalLanguage ModelingLanguage Modelling+2

Decoupled Alignment for Robust Plug-and-Play Adaptation

2024-06-03 · Haozheng Luo, Jiahao Yu, Wenxin Zhang, Jialong Li 외

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to …

Knowledge Distillation