Related papers: Farsighted Risk Mitigation of Lateral Movement Usi…

APT, known as Advanced Persistent Threat, is a difficult challenge for cyber defence. These threats make many traditional defences ineffective as the vulnerabilities exploited by these threats are insiders who have access to and are within…

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…

Large Language Models (LLMs) are increasingly deployed in settings where Chain-of-Thought (CoT) is interpreted by users. This creates a new safety risk: attackers may manipulate the model's observable CoT to make malicious behaviors. In…

Over the years, honeypots emerged as an important security tool to understand attacker intent and deceive attackers to spend time and resources. Recently, honeypots are being deployed for Internet of things (IoT) devices to lure attackers,…

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Downtime of industrial assets such as wind turbines and medical imaging devices comes at a sharp cost. To avoid such downtime costs, companies seek to initiate maintenance just before failure. Unfortunately, this is challenging for the…

Current tools and systems of detecting vulnerabilities simply alert the administrator of attempted attacks against his network or system. However, generally, the huge number of alerts to analyze and the amount time required to update…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Learning in MDPs with highly complex state representations is currently possible due to multiple advancements in reinforcement learning algorithm design. However, this incline in complexity, and furthermore the increase in the dimensions of…

With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their complex reasoning processes introduce new and largely unexplored…

Attacks on Industrial Control Systems (ICS) can lead to significant physical damage. While offline safety and security assessments can provide insight into vulnerable system components, they may not account for stealthy attacks designed to…

The cybersecurity of smart grids has become one of key problems in developing reliable modern power and energy systems. This paper introduces a non-stationary adversarial cost with a variation constraint for smart grids and enables us to…

Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, policy-centric loop, causing attack discovery to suffer from…

In the edge computing paradigm, mobile devices offload the computational tasks to an edge server by routing the required data over the wireless network. The full potential of edge computing becomes realized only if a smart device selects…

Historically, enterprise network reconnaissance is an active process, often involving port scanning. However, as routers and switches become more complex, they also become more susceptible to compromise. From this vantage point, an attacker…

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

The proliferation of location-based social networks (LBSNs) has provided the community with an abundant source of information that can be exploited and used in many different ways. LBSNs offer a number of conveniences to its participants,…

Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures. Despite significant progress, a majority of today's commercial solutions are…

Backdoor attacks pose a serious threat to deep reinforcement learning (DRL). Current defenses typically rely on reward anomalies to reverse-engineer triggers and model finetuning to remove backdoors. However, complex trigger patterns…