Related papers: Honeyval: A Comprehensive Evaluation Framework for…

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models (LLMs). By systematically applying carefully engineered prompts, we…

Attacks by Advanced Persistent Threats (APTs) have been shown to be difficult to detect using traditional signature- and anomaly-based intrusion detection approaches. Deception techniques such as decoy objects, often called honey items, may…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…

Increasing complexity in software systems places a growing demand on reasoning tools that unlock vulnerabilities manifest in source code. Many current approaches focus on vulnerability analysis as a classifying task, oversimplifying the…

Applications of Large Language Models~(LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions. Their inherent non-determinism,…

Evaluating the capabilities of Large Language Models (LLMs) has traditionally relied on static benchmark datasets, human assessments, or model-based evaluations - methods that often suffer from overfitting, high costs, and biases.…

The remarkable reasoning and code generation capabilities of large language models (LLMs) have spurred significant interest in applying LLMs to enable task automation in digital chip design. In particular, recent work has investigated early…

Lateral movement of advanced persistent threats has posed a severe security challenge. Due to the stealthy and persistent nature of the lateral movement, defenders need to consider time and spatial locations holistically to discover latent…

Fooling adversaries with traps such as honeytokens can slow down cyber attacks and create strong indicators of compromise. Unfortunately, cyber deception techniques are often poorly specified. Also, realistically measuring their…

Generating step-by-step "how-to" procedures is a key LLM capability: how-to advice is commonly requested in chatbots, and step-by-step planning is critical for reasoning over complex tasks. Yet, measuring and improving procedural validity…

This paper introduces LalaEval, a holistic framework designed for the human evaluation of domain-specific large language models (LLMs). LalaEval proposes a comprehensive suite of end-to-end protocols that cover five main components…

The rapid advancement of Large Language Models (LLMs) necessitates a deep understanding of their fundamental performance limits. This paper investigates the limits of LLM inference, focusing on hardware-imposed bottlenecks in…

Large Language Models (LLMs) are transforming how people find information, and many users turn nowadays to chatbots to obtain answers to their questions. Despite the instant access to abundant information that LLMs offer, it is still…

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat…

Large language models (LLMs) are expected to offer structured Markdown responses for the sake of readability in web chatbots (e.g., ChatGPT). Although there are a myriad of metrics to evaluate LLMs, they fail to evaluate the readability…

Today, internet and web services have become an inseparable part of our lives. Hence, ensuring continuous availability of service has become imperative to the success of any organization. But these services are often hampered by constant…

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce…

Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety…