Tootfinder

Inverting Trojans in LLMs
Zhengxing Li, Guangmingmei Yang, Jayaram Raghuram, David J. Miller, George Kesidis
https://arxiv.org/abs/2509.16203 https://arxiv…

Inverting Trojans in LLMs
While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based search over this space, central to many backdoor inversion methods. Second, there are ~30,000^k k-tuples to consider, k the token-length of a putative trigger. Third, for LLMs there is the need to blacklist tokens that have strong marginal associations with the pu…

Balancing Innovation and Oversight: AI in the U.S. Treasury and IRS: A Survey
Sohail Shaikh
https://arxiv.org/abs/2509.16294 https://arxiv.org/pdf/2509.162…

Balancing Innovation and Oversight: AI in the U.S. Treasury and IRS: A Survey
This paper explores how the U.S. Department of Treasury, particularly the Internal Revenue Service (IRS), is adopting artificial intelligence (AI) to modernize tax administration. Using publicly available information, the survey highlights the applications of AI for taxpayer support, operational efficiency, fraud detection, and audit optimization. Key initiatives include AI-powered chatbots, robotic process automation, machine learning for case selection, and advanced analytics for fraud preven…

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
Xuan Chen, Shiwei Feng, Zikang Xiong, Shengwei An, Yunshu Mao, Lu Yan, Guanhong Tao, Wenbo Guo, Xiangyu Zhang
https://arxiv.org/abs/2509.16950

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
Assessing the safety of autonomous driving (AD) systems against security threats, particularly backdoor attacks, is a stepping stone for real-world deployment. However, existing works mainly focus on pixel-level triggers that are impractical to deploy in the real world. We address this gap by introducing a novel backdoor attack against the end-to-end AD systems that leverage one or more other vehicles' trajectories as triggers. To generate precise trigger trajectories, we first use temporal log…

'PhantomCaptcha' hackers impersonate Ukrainian president’s office in attack on war relief workers https://therecord.media/phantomcaptcha-spearphishing-campaign-ukraine-war-relief-groups

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation
Yu Xia, Rui Zhong, Zeyu Song, Wei Yang, Junchen Wan, Qingpeng Cai, Chi Lu, Peng Jiang
https://arxiv.org/abs/2508.15388

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation
The extensive world knowledge and powerful reasoning capabilities of large language models (LLMs) have attracted significant attention in recommendation systems (RS). Specifically, The chain of thought (CoT) has been shown to improve the performance of LLMs on complex reasoning tasks for RS. However, due to the fact that LLMs often suffer from hallucination issues, there is no guarantee that their reasoning CoT is effective. A key challenge is to further enhance the recommendation capabilities …

Agora que fomos lembrados de como calor é uma bosta, concordamos todos que devemos trazer o inverno de volta, não é? #VoltaFrozen

Joint Resource Optimization Over Licensed and Unlicensed Spectrum in Spectrum Sharing UAV Networks Against Jamming Attacks
Rui Ding, Fuhui Zhou, Yuhang Wu, Qihui Wu, Tony Q. S. Quek
https://arxiv.org/abs/2507.17261

Joint Resource Optimization Over Licensed and Unlicensed Spectrum in Spectrum Sharing UAV Networks Against Jamming Attacks
Unmanned aerial vehicle (UAV) communication is of crucial importance in realizing heterogeneous practical wireless application scenarios. However, the densely populated users and diverse services with high data rate demands has triggered an increasing scarcity of UAV spectrum utilization. To tackle this problem, it is promising to incorporate the underutilized unlicensed spectrum with the licensed spectrum to boost network capacity. However, the openness of unlicensed spectrum makes UAVs suscep…

Ransomware gang steals meeting videos, financial secrets from fence wholesaler https://therecord.media/ransomware-gang-steals-meeting-video-fence-manufacturer

CISA warns of Apple zero-day used in targeted cyberattacks https://therecord.media/cisa-warns-of-apple-zero-day

As scientists show they can read inner speech, brain implant ‘pioneers’ fight for neural data privacy, access rights https://therecord.media/neural-data-privacy-brain-implants