MISA: Online Defense of Trojaned Models using Misattributions
Recent studies have shown that neural networks are vulnerable to Trojan attacks, where a network is trained to respond to specially crafted trigger patterns in the inputs in specific and potentially malicious ways. This paper proposes MISA, a new online approach to detect Trojan triggers for neural networks at inference time. Our approach is based on a novel notion called misattributions, which captures the anomalous manifestation of a Trojan activation in the feature space. Given an input image and the corresponding output prediction, our algorithm first computes the model's attribution on different features. It then statistically analyzes these attributions to ascertain the presence of a Trojan trigger. Across a set of benchmarks, we show that our method can effectively detect Trojan triggers for a wide variety of trigger patterns, including several recent ones for which there are no known defenses. Our method achieves 96% AUC for detecting images that include a Trojan trigger without any assumptions on the trigger pattern.
Code (0)
등록된 구현이 없습니다.
Tasks
Traffic Sign RecognitionSimilar Papers 제목 키워드 기반
Addressing Social Misattributions of Large Language Models: An HCXAI-based Approach
Human-centered explainable AI (HCXAI) advocates for the integration of social aspects into AI explanations. Central to the HCXAI discourse is the Social Transparency (ST) framework, which aims to make the socio-organizat…
TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
An image encoder pre-trained by self-supervised learning can be used as a general-purpose feature extractor to build downstream classifiers for various downstream tasks. However, many studies showed that an attacker can …
Self-Supervised LearningCatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
The success of deep neural networks (DNNs) in real-world applications has benefited from abundant pre-trained models. However, the backdoored pre-trained models can pose a significant trojan threat to the deployment of d…
DNN TestingTopological Detection of Trojaned Neural Networks
Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can lat…
On Trojan Signatures in Large Language Models of Code
Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the non-trojaned class parameters of the trojaned model, that can be …
Binary ClassificationDefect Detection