Our second estimator perturbs the empirical mean of the data set with noise calibrated to the empirical covariance,withoutreleasing thecovariance itself.

Unfortunately, in high dimensions, releasing the empirical mean leads to concrete privacy breaches [32, 41].

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first documented for Claude 3 Opus and later examined across additional large language models. In these setups, the word "training" refers to simulated training via prompts without parameter updates, so the observed effects are context conditioned shifts in behavior rather than preference learning. We study the phenomenon using an evaluation framework that compares preference optimization methods (BCO, DPO, KTO, and GRPO) across 15 models from four model families, measured along three axes: safety, harmlessness, and helpfulness. Our goal is to identify what causes alignment faking and when it occurs.

We introduce Guard Vector, a safety task vector computed as the parameter difference between a guardrail model (Guard Model) and a same-architecture pretrained language model. Composing this vector with a target language model yields a Target Guard Model (TGM). We then adapt TGM with a streaming-aware approach that combines prefix-based training and evaluation with a classifier that produces a single-token output. With this composition alone, TGM improves classification quality over established Guard Models across standard safety suites and enables language extensibility to Chinese, Japanese, and Korean, requiring neither additional training nor target language labels. It also demonstrates model portability across two widely used public guardrail backbones, Llama and Gemma. With prefix SFT (supervised fine-tuning), TGM preserves classification quality under streaming by aligning the behavior between prefix inputs and full-text inputs. The single-token output design increases throughput and reduces latency. Together, these components reduce data and compute requirements while promoting streaming-aware evaluation practices, thereby contributing to a more responsible AI ecosystem.

Learning-based autonomous driving systems are trained mostly on incident-free data, offering little guidance near safety-performance boundaries. Real crash reports contain precisely the contrastive evidence needed, but they are hard to use: narratives are unstructured, third-person, and poorly grounded to sensor views. We address these challenges by normalizing crash narratives to ego-centric language and converting both logs and crashes into a unified scene-action representation suitable for retrieval. At decision time, our system adjudicates proposed actions by retrieving relevant precedents from this unified index; an agentic counterfactual extension proposes plausible alternatives, retrieves for each, and reasons across outcomes before deciding. On a nuScenes benchmark, precedent retrieval substantially improves calibration, with recall on contextually preferred actions rising from 24% to 53%. The counterfactual variant preserves these gains while sharpening decisions near risk.

Understanding how urban environments are perceived in terms of safety is crucial for urban planning and policymaking. Traditional methods like surveys are limited by high cost, required time, and scalability issues. To overcome these challenges, this study introduces Large Multimodal Models (LMMs), specifically Llava 1.6 7B, as a novel approach to assess safety perceptions of urban spaces using street-view images. In addition, the research investigated how this task is affected by different socio-demographic perspectives, simulated by the model through Persona-based prompts. Without additional fine-tuning, the model achieved an average F1-score of 59.21% in classifying urban scenarios as safe or unsafe, identifying three key drivers of perceived unsafety: isolation, physical decay, and urban infrastructural challenges. Moreover, incorporating Persona-based prompts revealed significant variations in safety perceptions across the socio-demographic groups of age, gender, and nationality. Elder and female Personas consistently perceive higher levels of unsafety than younger or male Personas. Similarly, nationality-specific differences were evident in the proportion of unsafe classifications ranging from 19.71% in Singapore to 40.15% in Botswana. Notably, the model's default configuration aligned most closely with a middle-aged, male Persona. These findings highlight the potential of LMMs as a scalable and cost-effective alternative to traditional methods for urban safety perceptions. While the sensitivity of these models to socio-demographic factors underscores the need for thoughtful deployment, their ability to provide nuanced perspectives makes them a promising tool for AI-driven urban planning.

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the integration of images significantly shifts the model's internal activations during the forward pass, diverging from those triggered by textual input. Moreover, the safety alignments of LLMs embedded within VLMs are not sufficiently robust to handle the activations discrepancies, making the models vulnerable to even the simplest jailbreaking attacks. To address this issue, we propose an \textbf{internal activation revision} approach that efficiently revises activations during generation, steering the model toward safer outputs. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity. In addition, we explore three strategies for constructing positive and negative samples and two approaches for extracting revision vectors, resulting in different variants of our method. Comprehensive experiments demonstrate that the internal activation revision method significantly improves the safety of widely used VLMs, reducing attack success rates by an average of 48.94\%, 34.34\%, 43.92\%, and 52.98\% on SafeBench, Safe-Unsafe, Unsafe, and MM-SafetyBench, respectively, while minimally impacting model helpfulness.

Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the evaluation of these techniques has so far been limited to single conditioning properties and synthetic settings. In this work, we conduct a comprehensive evaluation of various activation steering strategies, highlighting the property-dependent nature of optimal parameters to ensure a robust effect throughout generation. To address this issue, we propose Dynamic Activation Composition, an information-theoretic approach to modulate the steering intensity of one or more properties throughout generation. Our experiments on multi-property steering show that our method successfully maintains high conditioning while minimizing the impact of conditioning on generation fluency.

Amidst the growing interest in developing task-autonomous AI for automated mental health care, this paper addresses the ethical and practical challenges associated with the issue and proposes a structured framework that delineates levels of autonomy, outlines ethical requirements, and defines beneficial default behaviors for AI agents in the context of mental health support. We also evaluate ten state-of-the-art language models using 16 mental health-related questions designed to reflect various mental health conditions, such as psychosis, mania, depression, suicidal thoughts, and homicidal tendencies. The question design and response evaluations were conducted by mental health clinicians (M.D.s). We find that existing language models are insufficient to match the standard provided by human professionals who can navigate nuances and appreciate context. This is due to a range of issues, including overly cautious or sycophantic responses and the absence of necessary safeguards. Alarmingly, we find that most of the tested models could cause harm if accessed in mental health emergencies, failing to protect users and potentially exacerbating existing symptoms. We explore solutions to enhance the safety of current models. Before the release of increasingly task-autonomous AI systems in mental health, it is crucial to ensure that these models can reliably detect and manage symptoms of common psychiatric disorders to prevent harm to users. This involves aligning with the ethical framework and default behaviors outlined in our study. We contend that model developers are responsible for refining their systems per these guidelines to safeguard against the risks posed by current AI technologies to user mental health and safety. Trigger warning: Contains and discusses examples of sensitive mental health topics, including suicide and self-harm.

This brief discusses evolutionary game theory as a powerful and unified mathematical tool to study evolution of collective behaviours. It summarises some of my recent research directions using evolutionary game theory methods, which include i) the analysis of statistical properties of the number of (stable) equilibria in a random evolutionary game, and ii) the modelling of safety behaviours' evolution and the risk posed by advanced Artificial Intelligence technologies in a technology development race. Finally, it includes an outlook and some suggestions for future researchers.