Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges
In order to deploy deep neural networks (DNNs) in high-stakes scenarios, it is imperative that DNNs provide inference robust to external perturbations - both intentional and unintentional. Although the resilience of DNNs to intentional and unintentional perturbations has been widely investigated, a unified vision of these inherently intertwined problem domains is still missing. In this work, we fill this gap by providing a survey of the state of the art and highlighting the similarities of the proposed approaches.We also analyze the research challenges that need to be addressed to deploy resilient and secure DNNs. As there has not been any such survey connecting the resilience of DNNs to intentional and unintentional perturbations, we believe this work can help advance the frontier in both domains by enabling the exchange of ideas between the two communities.
Code (0)
등록된 구현이 없습니다.
Tasks
SurveySimilar Papers 제목 키워드 기반
Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises
Deep learning models, such as those used for face recognition and attribute prediction, are susceptible to manipulations like adversarial noise and unintentional noise, including Gaussian and impulse noise. This paper in…
AttributeFace RecognitionIntent DetectionThe emergence of critical stocks in market crash
In complex systems like financial market, risk tolerance of individuals is crucial for system resilience.The single-security price limit, designed as risk tolerance to protect investors by avoiding sharp price fluctuatio…
Leveraging Self-Supervised Training for Unintentional Action Recognition
Unintentional actions are rare occurrences that are difficult to define precisely and that are highly dependent on the temporal context of the action. In this work, we explore such actions and seek to identify the points…
Action RecognitionMalicious and Unintentional Disclosure Risks in Large Language Models for Code Generation
This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data…
Code GenerationLanguage ModelingLanguage ModellingLarge Language Model+1The Computational Structure of Unintentional Meaning
Speech-acts can have literal meaning as well as pragmatic meaning, but these both involve consequences typically intended by a speaker. Speech-acts can also have unintentional meaning, in which what is conveyed goes abov…