相关论文: Cognitive Cybersecurity for Artificial Intelligenc…

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

The widespread adoption of microservice architectures has given rise to a new set of software security challenges. These challenges stem from the unique features inherent in microservices. It is important to systematically assess and…

Large language models are increasingly used for mental health support, yet their conversational coherence alone does not ensure clinical appropriateness. Existing general-purpose safeguards often fail to distinguish between therapeutic…

The introduction of advanced reasoning capabilities have improved the problem-solving performance of large language models, particularly on math and coding benchmarks. However, it remains unclear whether these reasoning models are more or…

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Cyber-physical systems posit a complex number of security challenges due to interconnection of heterogeneous devices having limited processing, communication, and power capabilities. Additionally, the conglomeration of both physical and…

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component,…

Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…

Contemporary cybersecurity governance assumes that professionals apply risk reasoning. Yet major organisational failures persist despite investment in tools, staffing, and credentials. This study investigates the structural source of that…

Large language models (LLMs) are increasingly embedded in Computer Science (CS) classrooms to automate code generation, feedback, and assessment. However, their susceptibility to adversarial or ill-intentioned prompts threatens student…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Detecting cyber-anomalies and attacks are becoming a rising concern these days in the domain of cybersecurity. The knowledge of artificial intelligence, particularly, the machine learning techniques can be used to tackle these issues.…

Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and…

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

The incidence of cybersecurity attacks utilizing social engineering techniques has increased. Such attacks exploit the fact that in every secure system, there is at least one individual with the means to access sensitive information. Since…

Large language models (LLMs) are increasingly deployed behind safety guardrails such as system prompts and content filters, especially in settings where product teams cannot modify model weights. In practice these guardrails are typically…

Human cognitive capacities and the needs of human-centric solutions for "Industry 5.0" make humans an indispensable component in Cyber-Physical Systems (CPSs), referred to as Human-Cyber-Physical Systems (HCPSs), where AI-powered…

LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current defenses, and single-layer guardrails are bypassed with similar rates. We present CivicShield, a…

One source of software project challenges and failures is the systematic errors introduced by human cognitive biases. Although extensively explored in cognitive psychology, investigations concerning cognitive biases have only recently…

AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…