Simha Sethumadhavan

E. Manzhosov, A. Hastings, M. Pancholi, R. Piersma, M. T. I. Ziad and S. Sethumadhavan, "Revisiting Residue Codes for Modern Memories," in IEEE Micro, vol. 43, no. 4, pp. 53-61, July-Aug. 2023, doi: 10.1109/MM.2023.3273489.

Abstract: This article shows how residue codes, traditionally used for compute rather than storage error correction, can be applied to memories with surprising results. We show that adapting residue codes to modern memory systems offers a level of error correction… Show more

E. Manzhosov, A. Hastings, M. Pancholi, R. Piersma, M. T. I. Ziad and S. Sethumadhavan, "Revisiting Residue Codes for Modern Memories," in IEEE Micro, vol. 43, no. 4, pp. 53-61, July-Aug. 2023, doi: 10.1109/MM.2023.3273489.

Abstract: This article shows how residue codes, traditionally used for compute rather than storage error correction, can be applied to memories with surprising results. We show that adapting residue codes to modern memory systems offers a level of error correction comparable to those of traditional schemes, such as Reed–Solomon, but with fewer bits of storage. For instance, our adaptation of residue codes—multiuse error-correcting code (MUSE ECC)—can offer ChipKill protection using approximately 30% fewer bits. We use the storage gains to hold the metadata needed for emerging security functionality, such as memory tagging, or to provide better detection capabilities against Rowhammer attacks. In a system with memory tagging and MUSE, we achieve a 12% reduction in memory bandwidth utilization with the same error correction level as a traditional ECC baseline and without a noticeable performance loss. Thus, our work demonstrates a new, flexible primitive for co-designing reliability with security and performance.

URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10122478&isnumber=10167507 Show less

CLKSCREW: Exposing the perils of security oblivious energy management. Adrian Tang, Simha Sethumadhavan, and Sal Stolfo.
Preprint: http://www.cs.columbia.edu/~simha/preprint_USENIX17_clkscrew.pdf

Analog Computing in a Modern Context: A Linear Algebra Accelerator Case Study: Yipeng Huang, Ning Guo, Mingoo Seok, Yannis Tsividis, and Simha Sethumadhavan

For the paper on Hardware Enforced Statistical Privacy with Matthew Maycock. First work on discussing hardware support for Privacy.

Paper: Identifying Functionally Similar Code in Complex Codebases

w/ Fang-Hsiang Su, Jonathan Bell, Gail Kaiser

Poster Link: (http://www.cs.columbia.edu/~simha/hc27AVdemo.jpg)
Demo Video: (https://drive.google.com/file/d/0B58y14EaaEacbUJoRkMzeTgtMDg/preview)

Adrian Tang & John Demme were honored at Hot Chips conference with a best poster award for their poster and demo titled "A Silicon AntiVirus Engine"​. Using a FPGA co-processor attached to an Intel Windows box, Adrian and John were able to use performance counter data from the Windows machine to identify unseen malware. They showed a live… Show more

Poster Link: (http://www.cs.columbia.edu/~simha/hc27AVdemo.jpg)
Demo Video: (https://drive.google.com/file/d/0B58y14EaaEacbUJoRkMzeTgtMDg/preview)

Adrian Tang & John Demme were honored at Hot Chips conference with a best poster award for their poster and demo titled "A Silicon AntiVirus Engine"​. Using a FPGA co-processor attached to an Intel Windows box, Adrian and John were able to use performance counter data from the Windows machine to identify unseen malware. They showed a live demo at the Hot Chips conference!

Adrian and John work with Simha Sethumadhavan & Sal Stolfo.
Show less

My students Adam Waksman (CS PhD) and Matthew Suozzo (CS Junior) have been recognized with a “Best Student Paper Award” at the CCS 2013. Our paper “FANCI: Identification of Stealthy Malicious Logic Using Boolean Functional Analysis” describes a method for detecting backdoors in hardware circuits before the hardware is manufactured and sent to the market. This is the first purely static analysis technique for detecting hardware backdoors. Papers with more than 50% student co-authors were… Show more

My students Adam Waksman (CS PhD) and Matthew Suozzo (CS Junior) have been recognized with a “Best Student Paper Award” at the CCS 2013. Our paper ��FANCI: Identification of Stealthy Malicious Logic Using Boolean Functional Analysis” describes a method for detecting backdoors in hardware circuits before the hardware is manufactured and sent to the market. This is the first purely static analysis technique for detecting hardware backdoors. Papers with more than 50% student co-authors were eligible for the best student paper award, and only three of 530 submissions received this honor. Show less

A Quantitative, Experimental Approach to Measuring Processor Side-Channel Security

Trustworthy Hardware from Untrustworthy Components

Outstanding Graduate Students in Computer Sciences

For dedication and outstanding service

Scalable Hardware Memory Disambiguation - One of the Most Industry Relevant Architecture Research Papers in 2004.