相关论文: Security Steerability is All You Need

Context: Software engineering (SE) researchers increasingly study Generative AI (GenAI) while also incorporating it into their own research practices. Despite rapid adoption, there is limited empirical evidence on how GenAI is used in SE…

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…

Generative AI's expanding footprint across numerous industries has led to both excitement and increased scrutiny. This paper delves into the unique security challenges posed by Generative AI, and outlines potential research directions for…

The rise of Generative AI (GenAI) brings about transformative potential across sectors, but its dual-use nature also amplifies risks. Governments globally are grappling with the challenge of regulating GenAI, balancing innovation against…

Generative artificial intelligence (GenAI) has the potential to improve healthcare through automation that enhances the quality and safety of patient care. Powered by foundation models that have been pretrained and can generate complex…

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive---new systems and models are being deployed in every…

Generative artificial intelligence (Gen AI) systems represent a critical technology with far-reaching implications across multiple domains of society. However, their deployment entails a range of risks and challenges that require careful…

Modern software systems are subjected to various types of uncertainties arising from context, environment, etc. To this end, self-adaptation techniques have been sought out as potential solutions. Although recent advances in self-adaptation…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…

Amidst escalating concerns about the detriments inflicted by AI systems, risk management assumes paramount importance, notably for high-risk applications as demanded by the European Union AI Act. Guidelines provided by ISO and NIST aim to…

Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this…

With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…

The rapid advancement of Generative Artificial Intelligence (GenAI) has introduced new opportunities for transforming higher education, particularly in fields that require analytical reasoning and regulatory compliance, such as…

Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding. This…

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs,…

The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect a community's values), which current systems fall short on.…

Generative Artificial Intelligence (GenAI) models such as LLMs, GPTs, and Diffusion Models have recently gained widespread attention from both the research and the industrial communities. This survey explores their application in network…