The City Attorney's Office sent the tech giants cease-and-desist letters this week telling them to stop profiting from 13 "face-swap" apps that are overwhelmingly used to target women and girls. Apple and Google have been ordered to take down apps that can "nudify" or "undress" people and told that they must stop profiting from the harmful technology, according to cease-and-desist letters sent to the companies seen by WIRED. On Thursday, San Francisco city attorney David Chiu sent legal notices to Apple and Google demanding that they remove from their app stores 13 face-swapping apps, which allow users to create AI-generated nonconsensual nude images. The letters say the Silicon Valley giants should stop "aiding and abetting" the sale of explicit deepfake images and "sever" business relationships with the app developers. "Generating non-consensual intimate images is illegal, harmful, and completely unacceptable," Chiu tells WIRED.

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during pretraining, they are hard to remove. In this work, we present a data-centric pretraining framework that builds safety into the model from the start. Our framework consists of four key steps: (i) Safety Filtering: building a safety classifier to classify webdata into safe and unsafe categories; (ii) Safety Rephrasing: we recontextualize unsafe webdata into safer narratives; (iii) Native Refusal: we synthetically generate pretraining datasets that actively teach models to refuse on unsafe content and the moral reasoning behind it, and (iv) Harmfulness-Tag annotated pretraining: we flag unsafe content during pretraining using a special token, and use it to steer models away from unsafe generations at inference-time. Our safety-pretrained models reduce attack success rates from 38.8% to 8.4% on standard LLM safety benchmarks with no performance degradation on general tasks.

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing watermarking techniques typically prioritize robustness against removal attacks, unfortunately, they are vulnerable to spoofing attacks: malicious actors can subtly alter the meanings of LLM-generated responses or even forge harmful content, potentially misattributing blame to the LLM developer. To overcome this, we introduce a bi-level signature scheme, Bileve, which embeds fine-grained signature bits for integrity checks (mitigating spoofing attacks) as well as a coarse-grained signal to trace text sources when the signature is invalid (enhancing detectability) via a novel rank-based sampling strategy. Compared to conventional watermark detectors that only output binary results, Bileve can differentiate 5 scenarios during detection, reliably tracing text provenance and regulating LLMs. The experiments conducted on OPT-1.3B and LLaMA-7B demonstrate the effectiveness of Bileve in defeating spoofing attacks with enhanced detectability.

Warning: This paper contains inappropriate/harmful visual contents. While widespread access to the Internet and the rapid advancement of generative models boost people's creativity and productivity, the risk of encountering inappropriate or harmful content also increases.

'Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today.

Studies show that safety-tuned models may nevertheless divulge harmful information. In this work, we show that whether they do so depends significantly on who they are talking to, which we refer to as . In fact, we find manipulating user persona to be more effective for eliciting harmful content than certain more direct attempts to control model refusal. We study both natural language prompting and activation steering as intervention methods and show that activation steering is significantly more effective at bypassing safety filters.We shed light on the mechanics of this phenomenon by showing that even when model generations are safe, harmful content can persist in hidden representations and can be extracted by decoding from earlier layers. We also show we can predict a persona's effect on refusal given only the geometry of its steering vector. Finally, we show that certain user personas induce the model to form more charitable interpretations of otherwise dangerous queries.

Online gaming escaped Australia's social media ban - but critics say it's just as addictive Wednesday afternoons have become a ritual for 15-year-old Sadmir Perviz. It's a circuitous route from home in Perth to the Fiona Stanley Hospital - but it's worth it, he says, to sit down for a game of Dungeons & Dragons with people he may not know but with whom he shares a great deal in common. Sadmir and his board game companions are just some of the 300 patients at the gaming disorder clinic, Australia's only publicly-run institution of its type, helping patients wean themselves off excessive online gaming habits. The room where they meet is a simple space in a faceless hospital but in the corner, there's a pile of boardgames on a chair. Jenga, Uno and Sushi Go are also popular choices at the informal group which is attended by both patients and clinicians.

We introduce SynBullying, a synthetic multi-LLM conversational dataset for studying and detecting cyberbullying (CB). SynBullying provides a scalable and ethically safe alternative to human data collection by leveraging large language models (LLMs) to simulate realistic bullying interactions. The dataset offers (i) conversational structure, capturing multi-turn exchanges rather than isolated posts; (ii) context-aware annotations, where harmfulness is assessed within the conversational flow considering context, intent, and discourse dynamics; and (iii) fine-grained labeling, covering various CB categories for detailed linguistic and behavioral analysis. We evaluate SynBullying across five dimensions, including conversational structure, lexical patterns, sentiment/toxicity, role dynamics, harm intensity, and CB-type distribution. We further examine its utility by testing its performance as standalone training data and as an augmentation source for CB classification.

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction.