Related papers: The Violation State: Safety State Persistence in a…
Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises…
Automated text generation has been applied broadly in many domains such as marketing and robotics, and used to create chatbots, product reviews and write poetry. The ability to synthesize text, however, presents many potential risks, while…
As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of…
The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We…
For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat…
In this paper, we extended the method proposed in [21] to enable humans to interact naturally with autonomous agents through vocal and textual conversations. Our extended method exploits the inherent capabilities of pre-trained large…
In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited…
This study examines the impact of AI on human false memories -- recollections of events that did not occur or deviate from actual occurrences. It explores false memory induction through suggestive questioning in Human-AI interactions,…
AI is increasingly being used to assist fraud and cybercrime. However, it is unclear the extent to which current large language models can provide useful information for complex criminal activity. Working with law enforcement and policy…
Multiparty session types are designed to abstractly capture the structure of communication protocols and verify behavioural properties. One important such property is progress, i.e., the absence of deadlock. Distributed algorithms often…
Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow,…
AI-companion apps such as Replika, Chai, and Character.ai promise relational benefits-yet many boast session lengths that rival gaming platforms while suffering high long-run churn. What conversational design features increase consumer…
Large Language Models (LLMs) can now solve entire exams directly from uploaded PDF assessments, raising urgent concerns about academic integrity and the reliability of grades and credentials. Existing watermarking techniques either operate…
Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in…
The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma: to prevent misuse, they are forced to damage the model's…
Behavioural types provide a promising way to achieve lightweight, language-integrated verification for communication-centric software. However, a large barrier to the adoption of behavioural types is that the current state of the art…
The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This…
We evaluate how effectively platform-level parental controls moderate a mainstream conversational assistant used by minors. Our two-phase protocol first builds a category-balanced conversation corpus via PAIR-style iterative prompt…
Understanding sentence meanings and updating information states appropriately across time -- what we call "situational understanding" (SU) -- is a critical ability for human-like AI agents. SU is essential in particular for chat models,…
Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior…