The final talk in the session was Shen et al.'s "T-Edge: Trusted Heterogeneous Edge Computing," detailing a secure ARM/FPGA design using TrustZone for cloud resources. (https://www.acsac.org/2024/program/final/s282.html) 6/6
#TrustedExecution #CloudComputing #ARM #FPGA

The fourth paper in this session was Fasano et al.'s "Hypervisor Dissociative Execution: Programming Guests for Monitoring, Management, and Security," detailing HyDE, a method for external program control of guest systems. (https://www.acsac.org/2024/program/final/s236.html) 5/6
#CloudSecurity #VMs

After that came Dhar et al.'s "Confidential Computing with Heterogeneous Devices at Cloud-Scale", proposing a security controller to protect non-TEE DSA nodes in cloud workloads. (https://www.acsac.org/2024/program/final/s297.html) 4/6
#CloudSecurity #ConfidentialCloud

The second paper was Deng et al.'s "ConProv: A Container-Aware Provenance System for Attack Investigation," presenting a novel approach to enhance container security investigations through precise provenance analysis. (https://www.acsac.org/2024/program/final/s230.html) 3/6
#ContainerSecurity #Provenance

First in the session came Chen et al.'s "CubeVisor: A Multi-realm Architecture Design for Running VM with ARM CCA" that introduces a secure, low-overhead virtualization model for ARM platforms. (https://www.acsac.org/2024/program/final/s93.html) 2/6
#Virtualization #ARM #Cybersecurity

Finally, we had Rahman et al.'s "Towards a Taxonomy of Challenges in Security Control Implementation", who propose a taxonomy of 73 challenges to enhance cyber defense. (https://www.acsac.org/2024/program/final/s366.html) 6/6
#Cybersecurity #Securityanalysis #Securitychallenges

Fourth was Zhang et al.'s "Stealing Watermarks of Large Language Models via Mixed Integer Programming," showcasing an attack that can compromise state-of-the-art watermark schemes. (https://www.acsac.org/2024/program/final/s355.html) 5/6
#AI #Watermarking #Cybersecurity

Third came Song et al.'s "Not All Tokens Are Equal: Membership Inference Attacks Against Fine-tuned Language Models" which introduces a practical attack method WEL-MIA for privacy threats in language models. (https://www.acsac.org/2024/program/final/s467.html) 4/6
#MembershipInference #ML #Cybersecurity

The second paper in this session was Bhusal et al.'s "SECURE: Benchmarking Large Language Models for Cybersecurity," introducing a benchmark to assess LLMs in realistic cybersecurity scenarios. (https://www.acsac.org/2024/program/final/s431.html) 3/6
#LLM #Cybersecurity #Benchmarking