Related papers: On Ladder Logic Bombs in Industrial Control System…

The widespread adoption of Large Language Models (LLMs) has heightened concerns about their security, particularly their vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs. While prior research…

Malicious examples are crucial for evaluating the robustness of machine learning algorithms under attack, particularly in Industrial Control Systems (ICS). However, collecting normal and attack data in ICS environments is challenging due to…

Networked Programmable Logic Controllers (PLCs) are proprietary industrial devices utilized in critical infrastructure that execute control logic applications in complex proprietary runtime environments that provide standardized access to…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

Batch prompting, which combines a batch of multiple queries sharing the same context in one inference, has emerged as a promising solution to reduce inference costs. However, our study reveals a significant security vulnerability in batch…

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Malware and other suspicious software often hide behaviors and components behind logic bombs and context-sensitive execution paths. Uncovering these is essential to react against modern threats, but current solutions are not ready to detect…

Programmable Logic Controllers (PLCs) provide a prominent choice of implementation platform for safety-critical industrial control systems. Formal verification provides ways of establishing correctness guarantees, which can be quite…

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a…

The critical challenge of prompt injection attacks in Large Language Models (LLMs) integrated applications, a growing concern in the Artificial Intelligence (AI) field. Such attacks, which manipulate LLMs through natural language inputs,…

Secure Multi-Party Computation (MPC) is an important enabling technology for data privacy in modern distributed applications. Currently, proof methods for low-level MPC protocols are primarily manual and thus tedious and error-prone, and…

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…

Vulnerability is a weakness, shortcoming or flaw in the system or network infrastructure which can be used by an attacker to harm the system, disrupt its normal operation and use it for his financial, competitive or other motives or just…

The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-parameter scale. The capabilities of VLAs stem primarily from…

In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large Language Models (LLMs) have made strides in automated code…

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such…

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…