A Formalization of Robustness for Deep Neural Networks
Deep neural networks have been shown to lack robustness to small input perturbations. The process of generating the perturbations that expose the lack of robustness of neural networks is known as adversarial input generation. This process depends on the goals and capabilities of the adversary, In this paper, we propose a unifying formalization of the adversarial input generation process from a formal methods perspective. We provide a definition of robustness that is general enough to capture different formulations. The expressiveness of our formalization is shown by modeling and comparing a variety of adversarial attack techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Evaluating the Robustness of Proof Autoformalization in Lean 4
Proof autoformalization aims to translate a mathematical informal proof written in natural language into a formal proof in a formal language such as Lean~4. Several works have developed LLM-based models for proof autofor…
Evaluating Autoformalization Robustness via Semantically Similar Paraphrasing
Large Language Models (LLMs) have recently emerged as powerful tools for autoformalization. Despite their impressive performance, these models can still struggle to produce grounded and verifiable formalizations. Recent …
Re-formalization of Individual Fairness
The notion of individual fairness is a formalization of an ethical principle, "Treating like cases alike," which has been argued such as by Aristotle. In a fairness-aware machine learning context, Dwork et al. firstly fo…
FairnessReformalization of the Jordan Curve Theorem
We present a case study in reformalization, a variant of autoformalization in which the input proof is not natural language but a formal development in a different proof assistant. Concretely, we report three reformaliza…
By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They Encode
Formalizing legal provisions promises machine-accessible law and automated legal reasoning, and recent LLMs make it tempting to generate such formalizations directly from statutory text. However, any formalization makes …
Legal Reasoning