相关论文: Security Steerability is All You Need
Most safety testing efforts for large language models (LLMs) today focus on evaluating foundation models. However, there is a growing need to evaluate safety at the application level, as components such as system prompts, retrieval…
Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain where inaccurate or misleading information can cause severe…
Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs…
Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…
The integration of generative artificial intelligence (GenAI) into 6G networks promises substantial performance gains while simultaneously exposing novel security vulnerabilities rooted in multimodal data processing and autonomous…
Over the last decade, Artificial Intelligence (AI) has become increasingly popular, especially with the use of chatbots such as ChatGPT, Gemini, and DALL-E. With this rise, large language models (LLMs) and Generative AI (GenAI) have also…
Despite the transformative impact of Artificial Intelligence (AI) across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code…
The rapid integration of Generative AI (GenAI) and Large Language Models (LLMs) in sectors such as education and healthcare have marked a significant advancement in technology. However, this growth has also led to a largely unexplored…
The rise of Generative AI (GenAI) has reshaped the cybersecurity landscape by enabling new attack vectors and lowering the barrier for executing advanced social engineering campaigns. This study conducts an empirical analysis of…
Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of…
Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…
Generative AI (genAI) tools promise productivity gains, yet miscalibrated trust and usage friction still hinder adoption. Moreover, genAI can be exclusionary, failing to adequately support diverse users. One such aspect of diversity is…
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…
The dawn of Generative Artificial Intelligence (GAI), characterized by advanced models such as Generative Pre-trained Transformers (GPT) and other Large Language Models (LLMs), has been pivotal in reshaping the field of data analysis,…
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,…
This whitepaper highlights the dual importance of securing generative AI (genAI) platforms and leveraging genAI for cybersecurity. As genAI technologies proliferate, their misuse poses significant risks, including data breaches, model…
The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…
As software security threats continue to evolve, the demand for innovative ways of securing coding has tremendously grown. The integration of Generative AI (GenAI) into software development holds significant potential for improving secure…
LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the…
As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known as jailbreaks. The…