Search Results for author:
Found 13 papers, 2 papers with code
BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
To this end, in this paper, we propose a novel backdoor leverage attack against c-MADRL, BLAST, which attacks the entire multi-agent team by embedding the backdoor only in a single agent.
A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
To this end, in this paper, we propose a novel backdoor attack against c-MADRL, which attacks the entire multi-agent team by embedding the backdoor only in a single agent.
Power Optimization and Deep Learning for Channel Estimation of Active IRS-Aided IoT
In the second case, when the transmit power at the IoT devices is fixed, there exists an optimal reflective power at active IRS.
Large language models in bioinformatics: applications and perspectives
Finally, this review summarizes the potential and prospects of large language models in solving bioinformatic problems.
Towards Better Vision-Inspired Vision-Language Models
In this paper we present a vision-inspired vision-language connection module dubbed as VIVL which efficiently exploits the vision cue for VL models.
Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup
In our research, we constructed a dataset, the Multimodal Advertisement Audition Dataset (MAAD), from real-world scenarios within Alipay, and conducted experiments to validate the reliability of our proposed strategy.
Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER
Our BGA-MNER consists of \texttt{image2text} and \texttt{text2image} generation with respect to entity-salient content in two modalities.
Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous Driving
We then design a spatial-temporal Trojan attack on DRL policies, where the trigger is hidden in a sequence of spatial and temporal traffic features, rather than a single instant state used in existing Trojan on SL and DRL tasks.
A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning
Deep reinforcement learning (DRL) has made significant achievements in many real-world applications.
The configuration and failed eruption of a complex magnetic flux rope above a δ sunspot region
A null point is located above the flux rope.
Solar and Stellar Astrophysics Space Physics
TAPInspector: Safety and Liveness Verification of Concurrent Trigger-Action IoT Systems
Trigger-action programming (TAP) is a popular end-user programming framework that can simplify the Internet of Things (IoT) automation with simple trigger-action rules.
Cryptography and Security Human-Computer Interaction Networking and Internet Architecture Software Engineering D.2.4; F.3.1; C.2.0
Automated Swirl Detection Algorithm (ASDA) and Its Application to Simulation and Observational Data
Comparisons between swirls detected in Bifrost numerical MHD simulations and both ground-based and space-borne observations, suggest that: 1) the spatial resolution of data plays a vital role in the total number and radii of swirls detected; and 2) noise introduced by seeing effects could decrease the detection rate of swirls, but has no significant influences in determining their inferred properties.
Solar and Stellar Astrophysics
A New Tool for CME Arrival Time Prediction Using Machine Learning Algorithms: CAT-PUMA
We demonstrate that CAT-PUMA is accurate and fast.
Solar and Stellar Astrophysics
