Rethinking Backdoor Detection Evaluation for Language Models
Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. Backdoor detection methods aim to detect whether a released model contains a backdoor, so that practitioners can avoid such vulnerabilities. While existing backdoor detection methods have high accuracy in detecting backdoored models on standard benchmarks, it is unclear whether they can robustly identify backdoors in the wild. In this paper, we examine the robustness of backdoor detectors by manipulating different factors during backdoor planting. We find that the success of existing methods highly depends on how intensely the model is trained on poisoned data during backdoor planting. Specifically, backdoors planted with either more aggressive or more conservative training are significantly more difficult to detect than the default ones. Our results highlight a lack of robustness of existing backdoor detectors and the limitations in current benchmark construction.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Rethinking Stealthiness of Backdoor Attack against NLP Models
Recent researches have shown that large natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack. Backdoor attacked models can achieve good performance on clean test…
Backdoor AttackData AugmentationSentiment AnalysisWord EmbeddingsRethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve …
Backdoor AttackDataset DistillationRethinking Backdoor Attacks
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing t…
Backdoor AttackRethinking the Backdoor Attacks' Triggers: A Frequency Perspective
Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean d…
Strong Backdoors for Default Logic
In this paper, we introduce a notion of backdoors to Reiter's propositional default logic and study structural properties of it. Also we consider the problems of backdoor detection (parameterised by the solution size) as…