paper-with-me

홈 › Papers

ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger

2023-04-27 · Jiazhao Li, Yijin Yang, Zhuofeng Wu, V. G. Vinod Vydiswaran, Chaowei Xiao

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such as GPT-4 pushing rewriting to extraordinary levels, such attacks are becoming even harder to detect. We conduct a comprehensive investigation of the role of black-box generative models as a backdoor attack tool, highlighting the importance of researching relative defense strategies. In this paper, we reveal that the proposed generative model-based attack, BGMAttack, could effectively deceive textual classifiers. Compared with the traditional attack methods, BGMAttack makes the backdoor trigger less conspicuous by leveraging state-of-the-art generative models. Our extensive evaluation of attack effectiveness across five datasets, complemented by three distinct human cognition assessments, reveals that Figure 4 achieves comparable attack performance while maintaining superior stealthiness relative to baseline methods.

📄 PDF Abstract BibTeX arXiv:2304.14475

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor Attack

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing

2022-01-09 · Lingfeng Shen, Haiyun Jiang, Lemao Liu, Shuming Shi

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threate…

Backdoor AttackText Classification

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

2024-08-21 · Ziqiang Li, Yueqi Zeng, Pengfei Xia, Lei Liu 외

With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the …

Backdoor Attack

Punctuation Matters! Stealthy Backdoor Attack for Language Models

2023-12-26 · Xuan Sheng, Zhicheng Li, Zhaoyang Han, Xiangmao Chang 외

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts w…

Backdoor Attack

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

2022-06-17 · Ganqu Cui, Lifan Yuan, Bingxiang He, Yangyi Chen 외

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense …

text similarity

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound

2023-07-17 · Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao 외

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where…

Backdoor Attackspeech-recognitionSpeech Recognition