The growing influence of Artificial Intelligence (AI) systems on decision-making in critical domains has exposed their potential to cause significant harms, often rooted in biases embedded across the AI lifecycle. While existing frameworks and taxonomies document bias or harms in isolation, they rarely establish systematic links between specific bias types and the harms they cause, particularly within real-world sociotechnical contexts. Technical fixes proposed to address AI biases are ill-equipped to address them and are typically applied after a system has been developed or deployed, offering limited preventive value. We propose ECHO, a novel framework for proactive AI harm anticipation through the systematic mapping of AI bias types to harm outcomes across diverse stakeholder and domain contexts. ECHO follows a modular workflow encompassing stakeholder identification, vignette-based presentation of biased AI systems, and dual (human-LLM) harm annotation, integrated within ethical matrices for structured interpretation. This human-centered approach enables early-stage detection of bias-to-harm pathways, guiding AI design and governance decisions from the outset. We validate ECHO in two high-stakes domains (disease diagnosis and hiring), revealing domain-specific, bias-to-harm patterns and demonstrating ECHO's potential to support anticipatory governance of AI systems

As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish clearly unsafe content from borderline cases, leading to problematic over-blocking or under-refusal of genuinely harmful content. We present Vision Language Safety Understanding (VLSU), a comprehensive framework to systematically evaluate multimodal safety through fine-grained severity classification and combinatorial analysis across 17 distinct safety patterns. Using a multi-stage pipeline with real-world images and human annotation, we construct a large-scale benchmark of 8,187 samples spanning 15 harm categories. Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures: while models achieve 90%-plus accuracy on clear unimodal safety signals, performance degrades substantially to 20-55% when joint image-text reasoning is required to determine the safety label. Most critically, 34% of errors in joint image-text safety classification occur despite correct classification of the individual modalities, further demonstrating absent compositional reasoning capabilities. Additionally, we find that models struggle to balance refusing unsafe content while still responding to borderline cases that deserve engagement. For example, we find that instruction framing can reduce the over-blocking rate on borderline content from 62.4% to 10.4% in Gemini-1.5, but only at the cost of under-refusing on unsafe content with refusal rate dropping from 90.8% to 53.9%. Overall, our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models, and provides a critical test bed to enable the next milestones in research on robust vision-language safety.

Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning algorithms, unlearning in sparse models has not yet been well studied. In this paper, we empirically find that the deleted data has an impact on the pruned topology in a sparse model. Motivated by the observation and the right to be forgotten, we define a new terminology ``un-pruning" to eliminate the impact of deleted data on model pruning. Then we propose an un-pruning algorithm to approximate the pruned topology driven by retained data. We remark that any existing unlearning algorithm can be integrated with the proposed un-pruning workflow and the error of un-pruning is upper-bounded in theory. Also, our un-pruning algorithm can be applied to both structured sparse models and unstructured sparse models. In the experiment, we further find that Membership Inference Attack (MIA) accuracy is unreliable for assessing whether a model has forgotten deleted data, as a small change in the amount of deleted data can produce arbitrary MIA results. Accordingly, we devise new performance metrics for sparse models to evaluate the success of un-pruning. Lastly, we conduct extensive experiments to verify the efficacy of un-pruning with various pruning methods and unlearning algorithms. Our code is released at https://github.com/NKUShaw/SparseModels .

Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the development of long-context reasoning, continual personalization, and knowledge consistency.Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.While Retrieval-Augmented Generation (RAG) introduces external knowledge in plain text, it remains a stateless workaround without lifecycle control or integration with persistent representations.Recent work has modeled the training and inference cost of LLMs from a memory hierarchy perspective, showing that introducing an explicit memory layer between parameter memory and external retrieval can substantially reduce these costs by externalizing specific knowledge. Beyond computational efficiency, LLMs face broader challenges arising from how information is distributed over time and context, requiring systems capable of managing heterogeneous knowledge spanning different temporal scales and sources. To address this challenge, we propose MemOS, a memory operating system that treats memory as a manageable system resource. It unifies the representation, scheduling, and evolution of plaintext, activation-based, and parameter-level memories, enabling cost-efficient storage and retrieval. As the basic unit, a MemCube encapsulates both memory content and metadata such as provenance and versioning. MemCubes can be composed, migrated, and fused over time, enabling flexible transitions between memory types and bridging retrieval with parameter-based learning. MemOS establishes a memory-centric system framework that brings controllability, plasticity, and evolvability to LLMs, laying the foundation for continual learning and personalized modeling.

The blockchain oracle problem, which refers to the challenge of injecting reliable external data into decentralized systems, remains a fundamental limitation to the development of trustless applications. While recent years have seen a proliferation of architectural, cryptographic, and economic strategies to mitigate this issue, no one has yet fully resolved the fundamental question of how a blockchain can gain knowledge about the off-chain world. In this position paper, we critically assess the role artificial intelligence (AI) can play in tackling the oracle problem. Drawing from both academic literature and practitioner implementations, we examine how AI techniques such as anomaly detection, language-based fact extraction, dynamic reputation modeling, and adversarial resistance can enhance oracle systems. We observe that while AI introduces powerful tools for improving data quality, source selection, and system resilience, it cannot eliminate the reliance on unverifiable off-chain inputs. Therefore, this study supports the idea that AI should be understood as a complementary layer of inference and filtering within a broader oracle design, not a substitute for trust assumptions.

Are there any conditions under which a generative model's outputs are guaranteed not to infringe the copyrights of its training data? This is the question of "provable copyright protection" first posed by Vyas, Kakade, and Barak (ICML 2023). They define near access-freeness (NAF) and propose it as sufficient for protection. This paper revisits the question and establishes new foundations for provable copyright protection -- foundations that are firmer both technically and legally. First, we show that NAF alone does not prevent infringement. In fact, NAF models can enable verbatim copying, a blatant failure of copy protection that we dub being tainted. Then, we introduce our blameless copy protection framework for defining meaningful guarantees, and instantiate it with clean-room copy protection. Clean-room copy protection allows a user to control their risk of copying by behaving in a way that is unlikely to copy in a counterfactual clean-room setting. Finally, we formalize a common intuition about differential privacy and copyright by proving that DP implies clean-room copy protection when the dataset is golden, a copyright deduplication requirement.

Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience. Through a study of 480 participants evaluating 3,840 query-response pairs, we examine how different refusal strategies affect user perceptions across varying motivations. Our findings reveal that response strategy largely shapes user experience, while actual user motivation has negligible impact. Partial compliance -- providing general information without actionable details -- emerges as the optimal strategy, reducing negative user perceptions by over 50% to flat-out refusals. Complementing this, we analyze response patterns of 9 state-of-the-art LLMs and evaluate how 6 reward models score different refusal strategies, demonstrating that models rarely deploy partial compliance naturally and reward models currently undervalue it. This work demonstrates that effective guardrails require focusing on crafting thoughtful refusals rather than detecting intent, offering a path toward AI safety mechanisms that ensure both safety and sustained user engagement.

The democratization of generative AI introduces new forms of human-AI interaction and raises urgent safety, ethical, and cybersecurity concerns. We develop a socio-technical explanation for how generative AI enables and scales cybercrime. Drawing on affordance theory and technological amplification, we argue that generative AI systems create new action possibilities for cybercriminals and magnify pre-existing malicious intent by lowering expertise barriers and increasing attack efficiency. To illustrate this framework, we conduct interrupted time series analyses of two large datasets: (1) 464,190,074 malicious IP address reports from AbuseIPDB, and (2) 281,115 cryptocurrency scam reports from Chainabuse. Using November 30, 2022, as a high-salience public-access shock, we estimate the counterfactual trajectory of reported cyber abuse absent the release, providing an early-warning impact assessment of a general-purpose AI technology. Across both datasets, we observe statistically significant post-intervention increases in reported malicious activity, including an immediate increase of over 1.12 million weekly malicious IP reports and about 722 weekly cryptocurrency scam reports, with sustained growth in the latter. We discuss implications for AI governance, platform-level regulation, and cyber resilience, emphasizing the need for multi-layer socio-technical strategies that help key stakeholders maximize AI's benefits while mitigating its growing cybercrime risks.

User authorization-based access privileges are a key feature in many safety-critical systems, but have not been extensively studied in the large language model (LLM) realm. In this work, drawing inspiration from such access control systems, we introduce sudoLLM, a novel framework that results in multi-role aligned LLMs, i.e., LLMs that account for, and behave in accordance with, user access rights. sudoLLM injects subtle user-based biases into queries and trains an LLM to utilize this bias signal in order to produce sensitive information if and only if the user is authorized. We present empirical results demonstrating that this approach shows substantially improved alignment, generalization, resistance to prefix-based jailbreaking attacks, and ``fails-closed''. The persistent tension between the language modeling objective and safety alignment, which is often exploited to jailbreak LLMs, is somewhat resolved with the aid of the injected bias signal. Our framework is meant as an additional security layer, and complements existing guardrail mechanisms for enhanced end-to-end safety with LLMs.