U.S. prosecutors have charged two Virginia brothers arrested on Wednesday with allegedly conspiring to steal sensitive information and destroy government databases after being fired from their jobs as federal contractors. […] Read More
The threat actor known as Silver Fox has been spotted orchestrating a false flag operation to mimic a Russian threat group in attacks targeting organizations in China. The search engine optimization (SEO) poisoning campaign leverages Microsoft Teams lures to trick unsuspecting users into downloading a malicious setup file that leads to the deployment of ValleyRAT […]
Russian telecommunications watchdog Roskomnadzor has blocked access to Apple’s FaceTime video conferencing platform and the Snapchat instant messaging service, claiming they’re being used to coordinate terrorist attacks. […] Read More
CISA released nine Industrial Control Systems (ICS) Advisories. These advisories provide timely information about current security issues, vulnerabilities, and exploits surrounding ICS. ICSA-25-338-01 Mitsubishi Electric GX Works2 ICSA-25-338-02 MAXHUB Pivot ICSA-25-338-03 Johnson Controls OpenBlue Mobile Web Application for OpenBlue Workplace ICSA-25-338-04 Johnson Controls iSTAR ICSA-25-338-05 Sunbird DCIM dcTrack and Power IQ ICSA-25-338-06 SolisCloud Monitoring Platform […]
On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Datacs.AI updates on arXiv.org arXiv:2504.07646v2 Announce Type: replace-cross
Abstract: The applicability of Large Language Models (LLMs) in temporal reasoning tasks over data that is not present during training is still a field that remains to be explored. In this paper we work on this topic, focusing on structured and semi-structured anonymized data. We not only develop a direct LLM pipeline, but also compare various methodologies and conduct an in-depth analysis. We identified and examined seventeen common temporal reasoning tasks in natural language, focusing on their algorithmic components. To assess LLM performance, we created the textit{Reasoning and Answering Temporal Ability} dataset (RATA), featuring semi-structured anonymized data to ensure reliance on reasoning rather than on prior knowledge. We compared several methodologies, involving SoTA techniques such as Tree-of-Thought, self-reflexion and code execution, tuned specifically for this scenario. Our results suggest that achieving scalable and reliable solutions requires more than just standalone LLMs, highlighting the need for integrated approaches.
arXiv:2504.07646v2 Announce Type: replace-cross
Abstract: The applicability of Large Language Models (LLMs) in temporal reasoning tasks over data that is not present during training is still a field that remains to be explored. In this paper we work on this topic, focusing on structured and semi-structured anonymized data. We not only develop a direct LLM pipeline, but also compare various methodologies and conduct an in-depth analysis. We identified and examined seventeen common temporal reasoning tasks in natural language, focusing on their algorithmic components. To assess LLM performance, we created the textit{Reasoning and Answering Temporal Ability} dataset (RATA), featuring semi-structured anonymized data to ensure reliance on reasoning rather than on prior knowledge. We compared several methodologies, involving SoTA techniques such as Tree-of-Thought, self-reflexion and code execution, tuned specifically for this scenario. Our results suggest that achieving scalable and reliable solutions requires more than just standalone LLMs, highlighting the need for integrated approaches. Read More
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimizationcs.AI updates on arXiv.org arXiv:2511.05747v2 Announce Type: replace
Abstract: Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, limiting deployment in resource-constrained settings. This paper investigates efficient CoT transfer across models of different scales and architectures through an adaptive reasoning summarization framework. The proposed method compresses reasoning traces via semantic segmentation with importance scoring, budget-aware dynamic compression, and coherence reconstruction, preserving critical reasoning steps while significantly reducing token usage. Experiments on 7{,}501 medical examination questions across 10 specialties show up to 40% higher accuracy than truncation under the same token budgets. Evaluations on 64 model pairs from eight LLMs (1.5B-32B parameters, including DeepSeek-R1 and Qwen3) confirm strong cross-model transferability. Furthermore, a Gaussian Process-based Bayesian optimization module reduces evaluation cost by 84% and reveals a power-law relationship between model size and cross-domain robustness. These results demonstrate that reasoning summarization provides a practical path toward efficient CoT transfer, enabling advanced reasoning under tight computational constraints. Code will be released upon publication.
arXiv:2511.05747v2 Announce Type: replace
Abstract: Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, limiting deployment in resource-constrained settings. This paper investigates efficient CoT transfer across models of different scales and architectures through an adaptive reasoning summarization framework. The proposed method compresses reasoning traces via semantic segmentation with importance scoring, budget-aware dynamic compression, and coherence reconstruction, preserving critical reasoning steps while significantly reducing token usage. Experiments on 7{,}501 medical examination questions across 10 specialties show up to 40% higher accuracy than truncation under the same token budgets. Evaluations on 64 model pairs from eight LLMs (1.5B-32B parameters, including DeepSeek-R1 and Qwen3) confirm strong cross-model transferability. Furthermore, a Gaussian Process-based Bayesian optimization module reduces evaluation cost by 84% and reveals a power-law relationship between model size and cross-domain robustness. These results demonstrate that reasoning summarization provides a practical path toward efficient CoT transfer, enabling advanced reasoning under tight computational constraints. Code will be released upon publication. Read More
Cloudflare on Wednesday said it detected and mitigated the largest ever distributed denial-of-service (DDoS) attack that measured at 29.7 terabits per second (Tbps). The activity, the web infrastructure and security company said, originated from a DDoS botnet-for-hire known as AISURU, which has been linked to a number of hyper-volumetric DDoS attacks over the past year. […]
As 2025 draws to a close, security professionals face a sobering realization: the traditional playbook for web security has become dangerously obsolete. AI-powered attacks, evolving injection techniques, and supply chain compromises affecting hundreds of thousands of websites forced a fundamental rethink of defensive strategies. Here are the five threats that reshaped web security this year, […]
Cybercriminals associated with a financially motivated group known as GoldFactory have been observed staging a fresh round of attacks targeting mobile users in Indonesia, Thailand, and Vietnam by impersonating government services. The activity, observed since October 2024, involves distributing modified banking applications that act as a conduit for Android malware, Group-IB said in a technical Read […]
AI in manufacturing set to unleash new era of profitAI News Manufacturing executives are wagering nearly half their modernisation budgets on AI, betting these systems will boost profit within two years. This aggressive capital allocation marks a definitive pivot. AI is now seen as the primary engine for financial performance. According to the Future-Ready Manufacturing Study 2025 by Tata Consultancy Services (TCS) and AWS, 88 percent
The post AI in manufacturing set to unleash new era of profit appeared first on AI News.
Manufacturing executives are wagering nearly half their modernisation budgets on AI, betting these systems will boost profit within two years. This aggressive capital allocation marks a definitive pivot. AI is now seen as the primary engine for financial performance. According to the Future-Ready Manufacturing Study 2025 by Tata Consultancy Services (TCS) and AWS, 88 percent
The post AI in manufacturing set to unleash new era of profit appeared first on AI News. Read More
