相关论文: Attention Hijacking in Trojan Transformers

This paper proposes MergeGuard, a novel methodology for mitigation of AI Trojan attacks. Trojan attacks on AI models cause inputs embedded with triggers to be misclassified to an adversary's target class, posing a significant threat to…

While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn,…

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

A recent trojan attack on deep neural network (DNN) models is one insidious variant of data poisoning attacks. Trojan attacks exploit an effective backdoor created in a DNN model by leveraging the difficulty in interpretability of the…

Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations, such as unavailability or being too large, or computational power limitations. Therefore, it is a common…

We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as features and modulation…

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

AI models are often regarded as valuable intellectual property due to the high cost of their development, the competitive advantage they provide, and the proprietary techniques involved in their creation. As a result, AI model stealing…

Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the…

Transformer models have excelled in natural language tasks, prompting the vision community to explore their implementation in computer vision problems. However, these models are still influenced by adversarial examples. In this paper, we…

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan…

As industry moves toward chiplet-based designs, the insertion of hardware Trojans poses a significant threat to the security of these systems. These systems rely heavily on cache coherence for coherent data communication, making coherence…

Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access to any triggered data, is the subject of ongoing research and…

Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing. Hence, attention is being extensively studied to investigate various linguistic capabilities of Transformers,…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Attention is fundamental to cognition, yet it remains a challenge to understand attention in tasks approaching real-world complexity. Here, we approached this problem by modeling gaze patterns of monkeys playing Pac-Man. We first show a…

Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep…

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that…

This study investigates the vulnerabilities of autonomous navigation and landing systems in Urban Air Mobility (UAM) vehicles. Specifically, it focuses on Trojan attacks that target deep learning models, such as Convolutional Neural…