Diffusion models have significantly advanced text-to-image generation, enabling the creation of highly realistic images conditioned on textual prompts and seeds. Given the considerable intellectual and economic value embedded in such prompts, prompt theft poses a critical security and privacy concern. In this paper, we investigate prompt-stealing attacks targeting diffusion models. We reveal that numerical optimization-based prompt recovery methods are fundamentally limited as they do not account for the initial random noise used during image generation. We identify and exploit a noise-generation vulnerability (CWE-339), prevalent in major image-generation frameworks, originating from PyTorch's restriction of seed values to a range of $2^{32}$ when generating the initial random noise on CPUs. Through a large-scale empirical analysis conducted on images shared via the popular platform CivitAI, we demonstrate that approximately 95% of these images' seed values can be effectively brute-forced in 140 minutes per seed using our seed-recovery tool, SeedSnitch. Leveraging the recovered seed, we propose PromptPirate, a genetic algorithm-based optimization method explicitly designed for prompt stealing. PromptPirate surpasses state-of-the-art methods, i.e., PromptStealer, P2HP, and CLIP-Interrogator, achieving an 8-11% improvement in LPIPS similarity. Furthermore, we introduce straightforward and effective countermeasures that render seed stealing, and thus optimization-based prompt stealing, ineffective. We have disclosed our findings responsibly and initiated coordinated mitigation efforts with the developers to address this critical vulnerability.

High-profile speech videos are prime targets for falsification, owing to their accessibility and influence. This work proposes VeriLight, a low-overhead and unobtrusive system for protecting speech videos from visual manipulations of speaker identity and lip and facial motion. Unlike the predominant purely digital falsification detection methods, VeriLight creates dynamic physical signatures at the event site and embeds them into all video recordings via imperceptible modulated light. These physical signatures encode semantically-meaningful features unique to the speech event, including the speaker's identity and facial motion, and are cryptographically-secured to prevent spoofing. The signatures can be extracted from any video downstream and validated against the portrayed speech content to check its integrity. Key elements of VeriLight include (1) a framework for generating extremely compact (i.e., 150-bit), pose-invariant speech video features, based on locality-sensitive hashing; and (2) an optical modulation scheme that embeds $>$200 bps into video while remaining imperceptible both in video and live. Experiments on extensive video datasets show VeriLight achieves AUCs $\geq$ 0.99 and a true positive rate of 100% in detecting falsified videos. Further, VeriLight is highly robust across recording conditions, video post-processing techniques, and white-box adversarial attacks on its feature extraction methods. A demonstration of VeriLight is available at https://mobilex.cs.columbia.edu/verilight.

Full-duplex dialog models aim to listen and speak simultaneously, delivering rapid responses to dynamic user input. Among different solutions to full duplexity, a native solution merges multiple channels in each time step, achieving the lowest latency. However, prevailing designs break down the textual monologue sentences for word-level alignment with audio streams, which degrades language modeling abilities. To help address this issue, we introduce natural monologues, which are composed by continuous sentences and waiting intervals, mimicking humanoid cognitive behavior in dialogs. We find a proper training paradigm to be critical for semantically aligning natural monologues with audio. To this end, we develop a dual training paradigm that alternates the position of the monologues, either leading or trailing the audio, across different training stages. A combination of our natural monologue and dual training strategy is applied in developing FLM-Audio, our 7B spoken dialog chatbot with native full-duplexity. As confirmed by experimental results, FLM-Audio achieves superior response qualities and chatting experiences while requiring significantly less training data.

West Lafayette, Indiana, USA Abstract--Zero-shot V oice Cloning (VC) and T ext-to-Speech (TTS) methods have advanced rapidly, enabling the generation of highly realistic synthetic speech and raising serious concerns about their misuse. While numerous detectors have been developed for English and Chinese, Spanish--spoken by over 600 million people worldwide--remains underrepresented in speech forensics. T o address this gap, we introduce HISPASpoof, the first large-scale Spanish dataset designed for synthetic speech detection and attribution. It includes real speech from public corpora across six accents and synthetic speech generated with six zero-shot TTS systems. We evaluate five representative methods, showing that detectors trained on English fail to generalize to Spanish, while training on HISPASpoof substantially improves detection. We also evaluate synthetic speech attribution performance on HISPASpoof, i.e., identifying the generation method of synthetic speech. HISPASpoof thus provides a critical benchmark for advancing reliable and inclusive speech forensics in Spanish. The rapid advancement of speech synthesis techniques has significantly transformed the area of audio generation and speech forensics. Recent Text-to-Speech (TTS) and V oice Cloning (VC) methods [1], [2], [3], [4], [5], [6] are now capable of producing highly realistic synthetic voices that closely mimic the spectral, prosodic, and linguistic traits of real human speech [7], [8], [9], [10].

The integration of Large Language Models (LLMs) into recommender systems has enabled zero-shot, personality-based personalization through prompt-based interactions, offering a new paradigm for user-centric recommendations. However, incorporating user personality traits via the OCEAN model highlights a critical tension between achieving psychological alignment and ensuring demographic fairness. To address this, we propose PerFairX, a unified evaluation framework designed to quantify the trade-offs between personalization and demographic equity in LLM-generated recommendations. Using neutral and personality-sensitive prompts across diverse user profiles, we benchmark two state-of-the-art LLMs, ChatGPT and DeepSeek, on movie (MovieLens 10M) and music (Last.fm 360K) datasets. Our results reveal that personality-aware prompting significantly improves alignment with individual traits but can exacerbate fairness disparities across demographic groups. Specifically, DeepSeek achieves stronger psychological fit but exhibits higher sensitivity to prompt variations, while ChatGPT delivers stable yet less personalized outputs. PerFairX provides a principled benchmark to guide the development of LLM-based recommender systems that are both equitable and psychologically informed, contributing to the creation of inclusive, user-centric AI applications in continual learning contexts.

Charlie Kirk's killer'identified' by law enforcement in manhunt after Trump indicated he knew assassin's motive Charlie Kirk's body arrives in hearse at Salt Lake City as devastated wife and family gather with JD Vance Trump's address to the nation hit by outrageous'fake' claim REVEALED: The truth about the'vanishing plane' five miles from Charlie Kirk's assassination... as private jet owner is unmasked And the armed militia mystery. FBI terror hunter blows the lid on search for Charlie Kirk's assassin... and the vital clue cops are desperate for'Shots fired' at UMass Boston: SWAT teams rush to hall of residence as terrified students sprint away from scene Elite sniper breaks down Charlie Kirk assassin's sick plot... and reveals tiny detail everyone's missed: The gun. Joe Rogan is speechless as he learns of Charlie Kirk's assassination on his podcast Fans claim NFL is'rigged' after bizarre Vikings play against Bears goes viral Biden insiders spew venom on Kamala Harris claiming her scathing critique of the former president is a'sloppy attempt at deflecting blame' for her failure Charlotte Tilbury reveals the secrets behind the Dallas Cowboys Cheerleaders' flawless look Americans are unknowingly eating endangered animals... as study finds grocery store meat is mislabeled Mom of Ukrainian stabbing suspect says'killer' is'NOT racist because he dates all kinds of girls' Dave Portnoy: Trump played a huge part in Charlie Kirk's death Charlie Kirk's assassin sniper's nest giving him a terrifying clear shot before he vanished into thin air Charlie Kirk's body to be flown home aboard Air Force Two in rare tribute Silenced by a bullet to the throat - then came the sneers. MAUREEN CALLAHAN's blistering rebuke as America faces greatest political crisis since the 60s Looking to level up your home entertainment setup this fall? Sony's newest budget smart TV is a strong contender Daily Mail journalists select and curate the products that feature on our site.

A series of corporate leaks show that Chinese technology companies function far more like their Western peers than one might imagine. A trove of internal documents leaked from a little-known Chinese company has pulled back the curtain on how digital censorship tools are being marketed and exported globally. Geedge Networks sells what amounts to a commercialized "Great Firewall" to at least four countries, including Kazakhstan, Pakistan, Ethiopia, and Myanmar. The groundbreaking leak shows in granular detail the capabilities this company has to monitor, intercept, and hack internet traffic. Researchers who examined the files described it as "digital authoritarianism as a service."

'Rapid developments' in manhunt for Charlie Kirk assassin after photos of'person of interest' were released: Live updates Charlie Kirk's body to be flown home aboard Air Force Two in rare tribute Dave Portnoy slams'insane' left in furious Charlie Kirk rant... but adds Donald Trump'played a part' in death Who are Charlie Kirk's parents and who was his mentor Bill Montgomery? Savannah Chrisley says she was set to join Charlie Kirk on his tour as she shares'heartbreak' over his death And the armed militia mystery. FBI terror hunter blows the lid on search for Charlie Kirk's assassin... and the vital clue cops are desperate for Shattered boyfriend of slain Ukrainian woman speaks out and reveals reason he WANTS everyone to watch the video: 'This is important to know' Elite sniper breaks down Charlie Kirk assassin's sick plot... and reveals tiny detail everyone's missed: The gun. Jimmy Kimmel reacts to assassination of Charlie Kirk: 'No finger pointing' Elon Musk unleashes explosive rant on Kirk assassination calling the left'the party of murder' 'Radicalized' Colorado school shooter who used revolver to open fire'again and again' at screaming kids is pictured Jennifer Lopez STILL living in $68M mansion she shared with Ben Affleck one year after listing, here's why Charlie Kirk's'incredibly strong' wife is too heartbroken to tell her children that'daddy isn't coming home' NBA's first openly-gay player Jason Collins reveals brain tumor as ex-Nets center starts cancer treatment MORE: Mystery of'fifth' 9/11 plane: United Airlines pilot claims his flight was intended to be hijacked The lab in charge of identifying the victims of the 9/11 terror attack has revealed why nearly half of their work remains unfinished more than two decades later. The New York City Office of the Chief Medical Examiner (OCME) said that approximately 1,100 people who were in the World Trade Center still haven't had their remains confirmed because of insufficient DNA evidence.

The image was taken during the G5 storm, the most extreme level of geomagnetic storm, in May. The reds were a level of intensity the photographer had never experienced. Breakthroughs, discoveries, and DIY tips sent every weekday. When the biggest geomagnetic storm in 20 years hit Earth in May 2024, photographer Kavan Chay was in Tumbledown Bay, New Zealand. Armed with a Nikon Z 7 astro-modified camera, Chay captured a absolutely spectacular shot (seen above) of the vibrant aurora that resulted from the G5-level storm.

Researchers say that in some cases the platforms are falling short on enforcing their own content moderation rules. Minutes after conservative political activist Charlie Kirk was shot yesterday at a speaking engagement at Utah Valley University, jarring videos of the incident began circulating on apps like TikTok, Instagram, and X. In the immediate aftermath, the majority of the videos viewed by WIRED did not contain content warnings. Many began autoplaying before viewers had the option to consent. And on X, an AI-generated recap of the incident falsely indicated that Kirk had survived the shooting.