paper-with-me

홈 › Papers

SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization

2021-12-08 · Wenbo Gou, Wen Shi, Jian Lou, Lijie Huang, Pan Zhou, Ruixuan Li

Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides. Adversarial vulnerability has been well-recognized as a critical security issue of deep neural network models, which requires prudent investigation. Despite its extensive yet separated studies in video and language tasks, current understanding of the adversarial robustness in vision-language joint tasks like NLVL is less developed. This paper therefore aims to comprehensively investigate the adversarial robustness of NLVL models by examining three facets of vulnerabilities from both attack and defense aspects. To achieve the attack goal, we propose a new adversarial attack paradigm called synonymous sentences-aware adversarial attack on NLVL (SNEAK), which captures the cross-modality interplay between the vision and language sides.

📄 PDF Abstract BibTeX arXiv:2112.04154

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial Robustness

Similar Papers 제목 키워드 기반

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

2026-03-29 · He Yang, Dongyi Lv, Song Ma, Wei Xi 외 arxiv

Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process…

SneakyPrompt: Jailbreaking Text-to-image Generative Models

2023-05-20 · Yuchen Yang, Bo Hui, Haolin Yuan, Neil Gong 외

Text-to-image generative models such as Stable Diffusion and DALL$\cdot$E raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones. To address these ethical concerns, safe…

Reinforcement Learning (RL)Semantic SimilaritySemantic Textual Similarity

Exploiting Class Probabilities for Black-box Sentence-level Attacks

2024-02-05 · Raha Moraffah, Huan Liu

Sentence-level attacks craft adversarial sentences that are synonymous with correctly-classified sentences but are misclassified by the text classifiers. Under the black-box setting, classifiers are only accessible throu…

Sentence

Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks

2019-05-28 · Pu Zhao, Siyue Wang, Cheng Gongye, Yanzhi Wang 외

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneak…

Overall - Test

SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions

2020-05-29 · ACL 2020 6 · Mao Ye, Chengyue Gong, Qiang Liu

State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that c…

text-classificationText Classification