Related papers: Attention Hijacking in Trojan Transformers
Visual attention is a fundamental mechanism in the human brain, and it inspires the design of attention mechanisms in deep neural networks. However, most of the visual attention studies adopted eye-tracking data rather than the direct…
Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…
Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems responsible for deciding which collision events to store impose…
Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that…
This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…
Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by the evidence that pure self-attention possesses a strong…
The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a growing interest in attention-based model explanations. Although attention weights do not…
Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…
Recent advancements in Artificial Intelligence namely in Deep Learning has heightened its adoption in many applications. Some are playing important roles to the extent that we are heavily dependent on them for our livelihood. However, as…
Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…
Attention-based transformers have become the standard architecture in many deep learning fields, primarily due to their ability to model long-range dependencies and handle variable-length input sequences. However, the attention mechanism…
Attention mechanisms have become integral in AI, significantly enhancing model performance and scalability by drawing inspiration from human cognition. Concurrently, the Attention Schema Theory (AST) in cognitive science posits that…
Neural network (NN) trojaning attack is an emerging and important attack model that can broadly damage the system deployed with NN models. Existing studies have explored the outsourced training attack scenario and transfer learning attack…
While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…
Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attackers have been shown to be effective against them. In this…
Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers…
Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intriguing class of spatially bounded, physically realizable,…
We introduce a new class of hardware trojans called interrupt-resilient trojans (IRTs). Our work is motivated by the observation that hardware trojan attacks on CPUs, even under favorable attack scenarios (e.g., an attacker with local…
Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…