9 accepted papers
As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present AUTOCONTROL ARENA, an automated framework for frontier AI ris…
As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely scenario-specific and model-centric. We introduce *OpenDeception*, a lightwe…
As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify. Existing research has overlooked the systematic assessment of LLMs’ criminal potential in realistic interactions, where criminal potential is defined as the risk of producing harmful behavi…
AI systems may exhibit deceptive behaviors that mislead developers about their capabilities, propensities, or actions. Such deception can take distinct forms across the development lifecycle: training subversion, evaluation gaming, and control evasion. We argue that the AI community should prioritiz…
LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly shapes subsequent actions. Small deviations in these thoughts can therefore propagate into unsafe behaviors, yet existing guardrails typically operate onl…
In the era of information explosion, users of online services are urgently waiting for timely and effective recommendations. In this paper, we present the first study on the responsiveness aspect of recommender system and present Responsive Online RecOmmender System (RØROS) based on Meta-Gradients U…
For pretrained language models such as Google’s BERT, recent research designs several input-adaptive inference mechanisms to improve the efficiency on cloud and edge devices. In this paper, we reveal a new attack surface on input-adaptive multi-exit BERT, where the adversary imperceptibly modifies t…
In this paper, we present a capacity-aware neuron steganography scheme (i.e., Cans) to covertly transmit multiple private machine learning (ML) datasets via a scheduled-to-publish deep neural network (DNN) as the carrier model. Unlike existing steganography schemes which treat the DNN parameters as…
Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners. Their reported empirical success however lacks solid theoretical interpretations for its inherent mechanism. In this paper,…