paper-with-me

Papers

Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges

2024-07-31 · Sazzad Sayyed, Milin Zhang, Shahriar Rifat, Ananthram Swami, Michael De Lucia, Francesco Restuccia

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.

📄 PDF Abstract BibTeX arXiv:2408.00193

Code (0)

등록된 구현이 없습니다.

Tasks

Survey

Similar Papers 제목 키워드 기반

Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises

2024-09-29 · Anubhooti Jain, Susim Roy, Kwanit Gupta, Mayank Vatsa 외

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 Detection

The emergence of critical stocks in market crash

2019-08-20

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

2022-09-23 · Enea Duka, Anna Kukleva, Bernt Schiele

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 Recognition

Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation

2025-03-27 · Rafiqul Rabin, Sean McGregor, Nick Judd

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+1

The Computational Structure of Unintentional Meaning

2019-06-03 · Mark K. Ho, Joanna Korman, Thomas L. Griffiths

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…