Related papers: AegisLLM: Scaling Agentic Systems for Self-Reflect…
Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strategic adaptation at scale, challenging security architectures…
Context: Large Language Models (LLMs) rely on static, pre-deployment safety mechanisms that cannot adapt to adversarial threats discovered after release. Objective: To design a software architecture enabling LLM-based systems to…
The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…
Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits…
Successful defense against dynamically evolving cyber threats requires advanced and sophisticated techniques. This research presents a novel approach to enhance real-time cybersecurity threat detection and response by integrating large…
As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…
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…
Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite their impressive performance, the potential for stronger…
Environmental, social, and governance (ESG) criteria are essential for evaluating corporate sustainability and ethical performance. However, professional ESG analysis is hindered by data fragmentation across unstructured sources, and…
The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…
We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This…
As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning…
Effort estimation is a crucial activity in agile software development, where teams collaboratively review, discuss, and estimate the effort required to complete user stories in a product backlog. Current practices in agile effort estimation…
Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent…
As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that…
As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust…
As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…
Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…
This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…
Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research agenda. Methods: Agentic LLMs are LLMs that (1) reason, (2)…