Agents with the FBI Nashville Field Office have been using new fingerprint-recognition technology to identify deceased individuals in the aftermath of Hurricane Helene. "When you're doing this, you still take extra care because that was a human and that was somebody's loved one. It was somebody's mother, brother, sister," FBI Special Agent Paul Durant, who has been with the FBI for five years, said in a statement. "It's tough, but it's rewarding to know that we can provide some answers to families who are suffering." The hurricane that devastated parts of Florida, Georgia, Tennessee, the Carolinas and Virginia has left more than 230 people dead since it made landfall on Sept. 27.

Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations. Moreover, they could be further used in downstream tasks such as classification. As previous work has shown, one can easily fool VAEs to produce unexpected latent representations and reconstructions for a visually slightly modified input. Here, we examine several objective functions for adversarial attacks construction proposed previously and present a solution to alleviate the effect of these attacks. Our method utilizes the Markov Chain Monte Carlo (MCMC) technique in the inference step that we motivate with a theoretical analysis.

Modern deep neural networks(DNNs) are vulnerable to adversarial samples. Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels. The existence of the sparse adversarial attack points out that DNNs are much more vulnerable than people believed, which is also a new aspect for analyzing DNNs. However, current sparse adversarial attack methods still have some shortcomings on both sparsity and invisibility. In this paper, we propose a novel two-stage distortion-aware greedy-based method dubbed as ''GreedyFool". Specifically, it first selects the most effective candidate positions to modify by considering both the gradient(for adversary) and the distortion map(for invisibility), then drops some less important points in the reduce stage.

The Israeli military "repeatedly" fired at UNIFIL headquarters and positions in southern Lebanon, injuring two members of the peacekeeping force, the United Nations says, as Israel presses on with its assault on Hezbollah. UNIFIL – the UN Interim Force in Lebanon – said on Thursday that two of its peacekeepers were injured after an Israeli tank "fired its weapon" at a guard tower at the group's headquarters, located in the border area town of Naqoura. The attack on the tower had caused the two peacekeepers to fall. "The injuries are fortunately, this time, not serious, but they remain in hospital," said UNIFIL in a statement. The Israeli soldiers also fired on a UN position – named "1-31"- in the village of Labbouneh, "hitting the entrance to the bunker where peacekeepers were sheltering, and damaging vehicles and a communications system", it said. The peacekeeping force reported that it had observed an Israeli military drone flying inside the UN position up to the bunker entrance.

During this election cycle, we've heard a lot from the presidential candidates about the struggles of America's workers and their families. Kamala Harris and Donald Trump each want to claim the mantle as the country's pro-worker candidate. Accordingly, union leaders took the stage not only at the Democratic National Convention, as usual, but at the Republican convention too. At the VP debate, J.D. Vance and Tim Walz offered competing views on how best to support workers. Surprisingly, one economic issue the candidates have yet to address is one in which millions of voters have a great deal at stake: the looming impact of new generative artificial intelligence (GenAI) technologies on work and livelihoods. The candidates' silence belies a stark reality: the next president will take office in a world already changed by GenAI--and heading for much greater disruption.

Although deep neural networks (DNN) have achieved great success, their applications in safety-critical areas are hindered due to their vulnerability to adversarial attacks. Some recent works have accordingly proposed to enhance the robustness of DNN from a dynamic system perspective. Following this line of inquiry, and inspired by the asymptotic stability of the general nonautonomous dynamical system, we propose to make each clean instance be the asymptotically stable equilibrium points of a slowly time-varying system in order to defend against adversarial attacks. We present a theoretical guarantee that if a clean instance is an asymptotically stable equilibrium point and the adversarial instance is in the neighborhood of this point, the asymptotic stability will reduce the adversarial noise to bring the adversarial instance close to the clean instance. Motivated by our theoretical results, we go on to propose a nonautonomous neural ordinary differential equation (ASODE) and place constraints on its corresponding linear time-variant system to make all clean instances act as its asymptotically stable equilibrium points.

Deep learning methods for graphs achieve remarkable performance on many tasks. However, despite the proliferation of such methods and their success, recent findings indicate that small, unnoticeable perturbations of graph structure can catastrophically reduce performance of even the strongest and most popular Graph Neural Networks (GNNs). Here, we develop GNNGuard, a general defense approach against a variety of training-time attacks that perturb the discrete graph structure. GNNGuard can be straightforwardly incorporated into any GNN. Its core principle is to detect and quantify the relationship between the graph structure and node features, if one exists, and then exploit that relationship to mitigate the negative effects of the attack.

Deep clustering integrates embedding and clustering together to obtain the optimal nonlinear embedding space, which is more effective in real-world scenarios compared with conventional clustering methods. However, the robustness of the clustering network is prone to being attenuated especially when it encounters an adversarial attack. A small perturbation in the embedding space will lead to diverse clustering results since the labels are absent. In this paper, we propose a robust deep clustering method based on adversarial learning. Specifically, we first attempt to define adversarial samples in the embedding space for the clustering network. Meanwhile, we devise an adversarial attack strategy to explore samples that easily fool the clustering layers but do not impact the performance of the deep embedding.

Russia's overnight attacks on Ukraine also left several people wounded in the southern city of Zaporizhzhia. Meanwhile, Ukrainian drones targeted a military airfield in the Maikop region of southern Russia. Local officials evacuated 40 people from a nearby village. Russia's missile strike on the Odesa region hit a Panamanian-registered ship on Wednesday night, Oleh Kiper said - two days after a Palau-flagged ship was attacked, leaving one dead on board. Another ship, which was said to be carrying 6,000 tonnes of corn, was attacked on Sunday.

Graph convolution networks (GCNs) have become effective models for graph classification. Similar to many deep networks, GCNs are vulnerable to adversarial attacks on graph topology and node attributes. Recently, a number of effective attack and defense algorithms have been designed, but no certificate of robustness has been developed for GCN-based graph classification under topological perturbations with both local and global budgets. In this paper, we propose the first certificate for this problem. Our method is based on Lagrange dualization and convex envelope, which result in tight approximation bounds that are efficiently computable by dynamic programming.