Large language models (LLMs) have recently revolutionized language processing tasks but have also brought ethical and legal issues. LLMs have a tendency to memorize potentially private or copyrighted information present in the training data, which might then be delivered to end users at inference time. When this happens, a naive solution is to retrain the model from scratch after excluding the undesired data. Although this guarantees that the target data have been forgotten, it is also prohibitively expensive for LLMs. Approximate unlearning offers a more efficient alternative, as it consists of ex post modifications of the trained model itself to prevent undesirable results, but it lacks forgetting guarantees because it relies solely on empirical evidence. In this work, we present DP2Unlearning, a novel LLM unlearning framework that offers formal forgetting guarantees at a significantly lower cost than retraining from scratch on the data to be retained. DP2Unlearning involves training LLMs on textual data protected using ε-differential privacy (DP), which later enables efficient unlearning with the guarantees against disclosure associated with the chosen ε. Our experiments demonstrate that DP2Unlearning achieves similar model performance post-unlearning, compared to an LLM retraining from scratch on retained data -- the gold standard exact unlearning -- but at approximately half the unlearning cost. In addition, with a reasonable computational cost, it outperforms approximate unlearning methods at both preserving the utility of the model post-unlearning and effectively forgetting the targeted information.

Adversarial patches are widely used to evaluate the robustness of object detection systems in real-world scenarios. These patches were initially designed to deceive single-modal detectors (e.g., visible or infrared) and have recently been extended to target visible-infrared dual-modal detectors. However, existing dual-modal adversarial patch attacks have limited attack effectiveness across diverse physical scenarios. To address this, we propose CDUPatch, a universal cross-modal patch attack against visible-infrared object detectors across scales, views, and scenarios. Specifically, we observe that color variations lead to different levels of thermal absorption, resulting in temperature differences in infrared imaging. Leveraging this property, we propose an RGB-to-infrared adapter that maps RGB patches to infrared patches, enabling unified optimization of cross-modal patches. By learning an optimal color distribution on the adversarial patch, we can manipulate its thermal response and generate an adversarial infrared texture. Additionally, we introduce a multi-scale clipping strategy and construct a new visible-infrared dataset, MSDrone, which contains aerial vehicle images in varying scales and perspectives. These data augmentation strategies enhance the robustness of our patch in real-world conditions. Experiments on four benchmark datasets (e.g., DroneVehicle, LLVIP, VisDrone, MSDrone) show that our method outperforms existing patch attacks in the digital domain. Extensive physical tests further confirm strong transferability across scales, views, and scenarios.

The latest attacks come as the Kremlin's spokesman, Dmitry Peskov, said that Russian President Vladimir Putin was ready to move towards a peace settlement with Ukraine but that Moscow's priority was to "achieve our goals". "President Putin has repeatedly spoken of his desire to bring the Ukrainian settlement to a peaceful conclusion as soon as possible. This is a long process, it requires effort, and it is not easy," he said in a televised interview. It has been nearly three-and-a-half years since Moscow launched its full-scale invasion of Ukraine. On Saturday, Ukrainian President Volodymyr Zelensky proposed a new round of talks with Moscow, aimed at restarting negotiations that halted last month.

MikeroweWORKS Foundation founder Mike Rowe joins'The Brian Kilmeade Show' to discuss how AI and robots threaten white-collar jobs, as the nation faces a need for blue-collar workers. Mike Rowe is sounding the alarm about the future of white and blue-collar jobs, and is urging young Americans to rethink their career choices due to threats from artificial intelligence. The former star of the shows "How America Works" and "Dirty Jobs" sat down with Fox News Radio host Brian Kilmeade to discuss the outlook for the U.S. job market amid recent developments from President Donald Trump's administration to invest in domestic energy and artificial intelligence. Trump visited Pittsburgh on July 15 to announce a 90 billion investment in data centers and other energy projects in Pennsylvania. Rowe was also present at the event, dubbed the Energy and Investment Summit, at Carnegie Mellon University.

Mallal says he wants to see a "broadly accessible and easy-to-use programme where artists are compensated for their work". Beeban Kidron, a cross-bench peer and leading campaigner against the government proposals, says AI film-making tools are "fantastic" but "at what point are they going to realise that these tools are literally built on the work of creators?" She adds: "Creators need equity in the new system or we lose something precious." YouTube says its terms and conditions allow Google to use creators' work for making AI models – and denies that all of YouTube's inventory has been used to train its models. Mallal calls his use of AI to make films "prompt craft", a phrase that uses the term for giving instructions to AI systems. When making the Ukraine film, he says he was amazed at how quickly a camera angle or lighting tone could be adjusted with a few taps on a keyboard.

As the old adage goes, "On the internet, nobody knows you're a dog". But in Australia it might soon be the case that everything from search engines and social media sites, to app stores and AI chatbots will have to know your age. The Albanese government trumpeted the passage of its legislation banning under 16s from social media – which will come into effect in December – but new industry codes developed by the tech sector and eSafety commissioner Julie Inman Grant under the Online Safety Act will probably have much larger ramifications for how Australians access the internet. Measures to be deployed by online services could include looking at your account history, or using facial age assurance and bank card checks. Identity checks using IDs such as drivers licences to keep children under 16 off social media will also apply to logged-in accounts for search engines from December, under an industry code that came into force at the end of June.

An Apple Watch saved his life after it used SOS to call for help when he had a stroke in his driveway. What if your Apple Watch or iPhone could alert you to a pregnancy before a test does? A new Apple-funded study suggests that this is now within reach. Researchers used a mix of behavioral and biometric data to train an artificial intelligence model. The system correctly predicted pregnancy in 92% of cases.

Fox News anchor Bret Baier examines the U.S. power supply on'Special Report.' POWER UP: A new White House study warns that electricity prices may spike due to artificial intelligence demand if the United States does not boost energy output. TURNED OFF: Google is making a push to ensure its AI, Gemini, is tightly integrated with Android systems by granting it access to core apps like WhatsApp, Messages, and Phone. The rollout of this change started on July 7, 2025, and it may override older privacy configurations unless you know how to disable Gemini on Android. Here's what you need to know. OPINION: DIGITAL DOMINANCE: The global race to harness the power of artificial intelligence (AI) has begun.

After reporting last week that the "raw" Jeffrey Epstein prison video posted by the FBI was likely modified in at least some ways (though there is no evidence that the footage was deceptively manipulated), WIRED reported on Tuesday that metadata analysis of the video shows approximately 2 minutes and 53 seconds were removed from one of two stitched-together clips. The United States Department of Homeland Security is facing controversy over DNA samples taken from approximately 133,000 migrant children and teens that the department added to a criminal database. Meanwhile, researcher Jeremiah Fowler published findings this week that more than 2 GB of extremely sensitive adoption-related data--including information about biological parents, children, and adoptive parents--was exposed and publicly accessible on the open internet. Roblox's new Trusted Connections feature includes age verification that uses AI to scan teens' video selfies and determine whether they can be granted access to unfiltered chatting with people they know. And as video deepfake capabilities mature--including AI tools that can even manipulate live video footage--AI "nudify" platforms are drawing millions of users and generating millions of dollars in revenue using tech from US companies.

AI humanoid robots are stepping into showrooms to greet customers, explain features and pour coffee. Why settle for a regular robot when you can have a robot coyote? That's the innovative question the U.S. Army Engineer Research and Development Center (ERDC) is answering as it rolls out robot coyotes for airfield wildlife control. These cybernetic prairie predators are a creative solution to a very real problem. Sign up for my FREE CyberGuy Report Get my best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox.