Related papers: Exploiting Logic Locking for a Neural Trojan Attac…
Modern machine learning (ML) models are expensive IP and business competitiveness often depends on keeping this IP confidential. This in turn restricts how these models are deployed; for example, it is unclear how to deploy a model…
Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…
Logic locking proposed to protect integrated circuits from serious hardware threats has been studied extensively over a decade. In these years, many efficient logic locking techniques have been proven to be broken. The state-of-the-art…
The increasing cost of integrated circuit (IC) fabrication has driven most companies to "go fabless" over time. The corresponding outsourcing trend gave rise to various attack vectors, e.g., illegal overproduction of ICs, piracy of the…
Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor…
Logic Encryption is one of the most popular hardware security techniques which can prevent IP piracy and illegal IC overproduction. It introduces obfuscation by inserting some extra hardware into a design to hide its functionality from…
Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…
Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the problem of Trojan…
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…
While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…
Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitatively model vulnerability patterns. This work pioneers the…
Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, but their vulnerability to trojan or backdoor attacks poses significant security risks. This paper explores the challenges and insights gained from…
In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…
Hateful meme detection aims to prevent the proliferation of hateful memes on various social media platforms. Considering its impact on social environments, this paper introduces a previously ignored but significant threat to hateful meme…
The semiconductor industry's paradigm shift towards fabless integrated circuit (IC) manufacturing has introduced security threats, including piracy, counterfeiting, hardware Trojans, and overproduction. In response to these challenges,…
There are increasing concerns about possible malicious modifications of integrated circuits (ICs) used in critical applications. Such attacks are often referred to as hardware Trojans. While many techniques focus on hardware Trojan…
We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications. A Trojan attack works by injecting a backdoor in the DNN while training; during inference, the…
Hardware Trojans have drawn the attention of academia, industry and government agencies. Effective detection mechanisms and countermeasures against such malicious designs can only be developed when there is a deep understanding of how…
Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…