相关论文: SafeText: A Benchmark for Exploring Physical Safet…

With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content generation, human-computer interaction, machine translation, and…

Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies…

Dark humor often relies on subtle cultural nuances and implicit cues that require contextual reasoning to interpret, posing safety challenges that current static benchmarks fail to capture. To address this, we introduce a novel multimodal,…

The increasing deployment of Large Vision-Language Models (LVLMs) raises safety concerns under potential malicious inputs. However, existing multimodal safety evaluations primarily focus on model vulnerabilities exposed by static image…

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…

Systems modeling practice lacks security analysis tools that can interface with modeling languages to facilitate security by design. Security by design is a necessity in the age of safety critical cyber-physical systems, where security…

With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interactions, pose a greater risk than single prompts; however,…

Machine generated text is increasingly difficult to distinguish from human authored text. Powerful open-source models are freely available, and user-friendly tools that democratize access to generative models are proliferating. ChatGPT,…

Recent advancements in model architectures and length extrapolation techniques have significantly extended the context length of large language models (LLMs), paving the way for their application in increasingly complex tasks. However,…

The current fascination with large language models, or LLMs, derives from the fact that many users lack the expertise to evaluate the quality of the generated text. LLMs may therefore appear more capable than they actually are. The…

Recent advancements in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. While various defence mechanisms have been proposed, there is a lack of comprehensive benchmarks that…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Safety evaluations of large language models (LLMs) typically focus on universal risks like dangerous capabilities or undesirable propensities. However, millions use LLMs for personal advice on high-stakes topics like finance and health,…

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains…

As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe outputs and guide safety, but such connections with safety are…

Language models for code (CodeLMs) have emerged as powerful tools for code-related tasks, outperforming traditional methods and standard machine learning approaches. However, these models are susceptible to security vulnerabilities, drawing…

More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense…

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

Strings are ubiquitous in code. Not all strings are created equal, some contain structure that makes them incompatible with other strings. CSS units are an obvious example. Worse, type checkers cannot see this structure: this is the latent…

As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce LifeTox, a dataset designed for identifying implicit toxicity within a broad…