Related papers: LATENT: LLM-Augmented Trojan Insertion and Evaluat…

Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploited for malicious purposes. Although safety alignment datasets have been introduced to…

Enterprise security faces escalating threats from sophisticated malware, compounded by expanding digital operations. This paper presents the first systematic evaluation of large language models (LLMs) to proactively identify indicators of…

Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated data cannot be fully trusted, as adversaries may implant Trojans during fine-tuning. We…

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

With the great advancements in large language models (LLMs), adversarial attacks against LLMs have recently attracted increasing attention. We found that pre-existing adversarial attack methodologies exhibit limited transferability and are…

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…

Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against…

In recent years, numerous large-scale cyberattacks have exploited Internet of Things (IoT) devices, a phenomenon that is expected to escalate with the continuing proliferation of IoT technology. Despite considerable efforts in attack…

This paper presents a critical examination of the surprising efficacy of Large Language Models (LLMs) in penetration testing. The paper thoroughly reviews the evolution of LLMs and their rapidly expanding capabilities which render them…

The Hardware Trojan (HT) problem can be thought of as a continuous game between attackers and defenders, each striving to outsmart the other by leveraging any available means for an advantage. Machine Learning (ML) has recently played a key…

The emergence of LLM (Large Language Model) integrated virtual assistants has brought about a rapid transformation in communication dynamics. During virtual assistant development, some developers prefer to leverage the system message, also…

In Natural Language Processing (NLP), intelligent neuron models can be susceptible to textual Trojan attacks. Such attacks occur when Trojan models behave normally for standard inputs but generate malicious output for inputs that contain a…

The recent progression of Large Language Models (LLMs) has witnessed great success in the fields of data-centric applications. LLMs trained on massive textual datasets showed ability to encode not only context but also ability to provide…

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Industrial Systems-on-Chips (SoCs) often comprise hundreds of thousands to millions of nets and millions to tens of millions of connectivity edges, making empirical evaluation of hardware-Trojan (HT) detectors on realistic designs both…

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

Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most…

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…