Pre-trained language models (PLMs) are known to be susceptible to perturbations to the input text, but existing works do not explicitly focus on linguistically grounded attacks, which are subtle and more prevalent in nature. In this paper, we study whether PLMs are agnostic to linguistically grounded attacks or not. To this end, we offer the first study addressing this, investigating different Indic languages and various downstream tasks. Our findings reveal that although PLMs are susceptible to linguistic perturbations, when compared to non-linguistic attacks, PLMs exhibit a slightly lower susceptibility to linguistic attacks. This highlights that even constrained attacks are effective. Moreover, we investigate the implications of these outcomes across a range of languages, encompassing diverse language families and different scripts.

Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives, often bypassing traditional reward-based defenses. Prior methods have primarily focused on reducing cumulative rewards; however, rewards are typically too generic to capture complex safety requirements effectively. As a result, focusing solely on reward reduction can lead to suboptimal attack strategies, particularly in safety-critical scenarios where more precise behavior manipulation is needed. To address these challenges, we propose RAT, a method designed for universal, targeted behavior attacks. RAT trains an intention policy that is explicitly aligned with human preferences, serving as a precise behavioral target for the adversary. Concurrently, an adversary manipulates the victim's policy to follow this target behavior. To enhance the effectiveness of these attacks, RAT dynamically adjusts the state occupancy measure within the replay buffer, allowing for more controlled and effective behavior manipulation. Our empirical results on robotic simulation tasks demonstrate that RAT outperforms existing adversarial attack algorithms in inducing specific behaviors. Additionally, RAT shows promise in improving agent robustness, leading to more resilient policies. We further validate RAT by guiding Decision Transformer agents to adopt behaviors aligned with human preferences in various MuJoCo tasks, demonstrating its effectiveness across diverse tasks.

The rise of chronic diseases and pandemics like COVID-19 has emphasized the need for effective patient data processing while ensuring privacy through anonymization and de-identification of protected health information (PHI). Anonymized data facilitates research without compromising patient confidentiality. This paper introduces expert small AI models developed using the LLM-in-the-loop methodology to meet the demand for domain-specific de-identification NER models. These models overcome the privacy risks associated with large language models (LLMs) used via APIs by eliminating the need to transmit or store sensitive data. More importantly, they consistently outperform LLMs in de-identification tasks, offering superior performance and reliability. Our de-identification NER models, developed in eight languages (English, German, Italian, French, Romanian, Turkish, Spanish, and Arabic) achieved f1-micro score averages of 0.966, 0.975, 0.976, 0.970, 0.964, 0.974, 0.978, and 0.953 respectively. These results establish them as the most accurate healthcare anonymization solutions, surpassing existing small models and even general-purpose LLMs such as GPT-4o. While Part-1 of this series introduced the LLM-in-the-loop methodology for bio-medical document translation, this second paper showcases its success in developing cost-effective expert small NER models in de-identification tasks. Our findings lay the groundwork for future healthcare AI innovations, including biomedical entity and relation extraction, demonstrating the value of specialized models for domain-specific challenges.

Conventional automatic incident detection (AID) has relied heavily on all incident reports exclusively for training and evaluation. However, these reports suffer from a number of issues, such as delayed reports, inaccurate descriptions, false alarms, missing reports, and incidents that do not necessarily influence traffic. Relying on these reports to train or calibrate AID models hinders their ability to detect traffic anomalies effectively and timely, even leading to convergence issues in the model training process. Moreover, conventional AID models are not inherently designed to capture the early indicators of any generic incidents. It remains unclear how far ahead an AID model can report incidents. The AID applications in the literature are also spatially limited because the data used by most models is often limited to specific test road segments. To solve these problems, we propose a deep learning framework utilizing prior domain knowledge and model-designing strategies. This allows the model to detect a broader range of anomalies, not only incidents that significantly influence traffic flow but also early characteristics of incidents along with historically unreported anomalies. We specially design the model to target the early-stage detection/prediction of an incident. Additionally, unlike most conventional AID studies, we use widely available data, enhancing our method's scalability. The experimental results across numerous road segments on different maps demonstrate that our model leads to more effective and early anomaly detection. Our framework does not focus on stacking or tweaking various deep learning models; instead, it focuses on model design and training strategies to improve early detection performance.

White House National Security Communications Advisor John Kirby responds to more questions over the aerial systems on'The Story.' White House National Security Communications Advisor John Kirby maintained that the government still lacks definitive answers regarding the nature of reported drone sightings as public frustration intensifies. "Many of the corroborated sightings have turned out to be piloted aircraft. I didn't say all of them, and what I said was those are the ones we were able to corroborate," Kirby said on "The Story." "There certainly is ones that we have not been able to, and we don't know the answer to it, and I strongly recommend that for folks that are seeing these things and documenting them to share that as they can with the Department of Homeland Security and the FBI." In a Wednesday letter to Biden, New Jersey Gov. Phil Murphy asked the president for more federal resources to address drone sightings, noting that the federal law limits the ability of state and local law enforcement to counter drones.

White House national security spokesman John Kirby addressed the sightings of'drones' over New Jersey's skies, denying that any evidence suggests a foreign adversary is responsible. An uptick in alleged drone sightings along the East Coast touched off a flurry of panicked calls for investigation on Friday from residents and state lawmakers, even as public officials stress the aircraft in question are, in fact, being flown lawfully, and a retired port authority aviation expert tells Fox News Digital that fears are overblown. The drone complaints began pouring in last month in New Jersey, where witnesses and residents first began reporting drone sightings off of coastal areas, including off of Cape May, a scenic town located outside of Atlantic City. More recently, lawmakers in New York, Connecticut, Pennsylvania and Maryland have reported new alleged drone sightings in their home states, with some witnesses alleging the aircraft in question have been the "size of cars" or seen flying above sensitive infrastructure or in restricted airspace. New Jersey Gov. Phil Murphy, a Democrat, told reporters on Friday he had written to President Biden to share his concerns about the fresh reports of unmanned aircraft systems (UAS) sightings in New Jersey airspace, and called for more federal resources to investigate the issue.

Residents and officials from multiple US states are demanding answers about mysterious drone sightings that have been blamed on everything from foreign governments to alien UFOs. Numerous'SUV-sized' craft first appeared in New Jersey in mid-November, and have since spread to New York, Pennsylvania and Connecticut. Drone sightings have also been reported in states such as Texas, Oklahoma and California as well as foreign countries such as Germany. But it's unclear whether these reports are related to the activity plaguing the Northeast. In New Jersey, the drones sometimes appear in groups and often remain in the same place for hours at a time, according to eyewitnesses.

Satellite images have spotted the Iranian'mothership' linked to the mysterious drones in New Jersey. The Shahid Bagheri drone carrier was last seen at its berth in the Iran Shipbuilding & Offshore Industries Complex on November 12, but an image taken 18 days later showed its docking station empty. That is around the same time New Jersey police started to be inundated with sightings of drones in the skies, flying in clusters and acting strangely. New Jersey Republican Rep Jeff Van Drew claimed this week there was'circumstantial evidence' that Iran's ship was releasing the drones from America's East Coast. Van Drew said that Iran made a deal with China'to purchase drones, a mothership and other technologies' for the drone attack on the US, a theory the Pentagon has dismissed.

Amazon is the latest tech giant to donate to Donald Trump's inaugural fund. The company plans to give 1m to the fund, first reported by the Wall Street Journal. Amazon follows Meta, Facebook's parent company, also handing over 1m to Trump's inaugural committee. OpenAI CEO Sam Altman said on Friday that he, too, would make a personal donation of 1m, first reported by Fox News. As Trump prepares to enter office for a second time, several tech titans are cozying up in hopes of favorable treatment for their businesses.

New Jersey resident Kristen Cobo captures video of approximately 8 suspected drones over a farm near her home on Dec. 12. Drone experts have little idea what the dozens of drone sightings over New Jersey could be, but have ruled out the possibility that they might be the work of a classified government program. They say the lack of a clear image or any residual hardware makes it difficult to make any guesses. "Until something is found, it's really difficult to say," said Brett Velicovich, Fox News contributor and CEO of Expert Drones. "We haven't seen any clear images."