Related papers: Attention Hijacking in Trojan Transformers

Trojan attacks embed perturbations in input data leading to malicious behavior in neural network models. A combination of various Trojans in different modalities enables an adversary to mount a sophisticated attack on multimodal learning…

We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel…

Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a…

In this paper, we propose a novel host-free Trojan attack with triggers that are fixed in the semantic space but not necessarily in the pixel space. In contrast to existing Trojan attacks which use clean input images as hosts to carry…

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,…

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive…

Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous…

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention…

Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-engineering methods only consider input space constraints,…

With the surge of Machine Learning (ML), An emerging amount of intelligent applications have been developed. Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and…

The threat of hardware Trojans (HTs) and their detection is a widely studied field. While the effort for inserting a Trojan into an application-specific integrated circuit (ASIC) can be considered relatively high, especially when trusting…

Hardware Trojans (HTs) have become a serious problem, and extermination of them is strongly required for enhancing the security and safety of integrated circuits. An effective solution is to identify HTs at the gate level via machine…

Logic locking and hardware Trojans are two fields in hardware security that have been mostly developed independently from each other. In this paper, we identify the relationship between these two fields. We find that a common structure that…

Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors within PVMs poses significant threats. Unfortunately, existing…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

In this paper we delve deep in the Transformer architecture by investigating two of its core components: self-attention and contextual embeddings. In particular, we study the identifiability of attention weights and token embeddings, and…

This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan detection defence across Vision, Text and Audio domains---thus termed as STRIP-ViTA. Specifically,…

The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention mechanisms used by…