Seungmin Baek

Seungmin Baek

Auto-generated profile, based on publicly available information

Seungmin Baek

Seoul National University, Seoul, South Korea

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2025
Verified
Conference Paper
Open access
SBSeungmin Baek
Seungmin Baek
MWMinbok Wi
Minbok Wi
SPSeonyong Park
Seonyong Park
HNHwayong Nam
Hwayong Nam
MKMichael Jaemin Kim
Michael Jaemin Kim
JAJung Ho Ahn
Jung Ho Ahn
A body of recent work has revealed that two different rows in a DRAM bank, from the perspective of a processor-memory interface, are connected to the same wordline but two separate row buffers (bitline sense amplifiers) in certain DRAM chips. Such a pair of rows is referred to as a ''coupled-row pair.'' Coupled-row pairs pose a substantial security threat as RowHammer bitflips can be caused not only by the conventional, adjacent aggressor rows but also by their coupled rows that are distant in physical address We investigate the impact of a coupled row on both FPGA-based infrastructure and server systems. In RowHammer attacks, coupled rows have hammering strength nearly identical to aggressor rows, with these attacks invisible to conventional, processor-side mitigation solutions. By exploiting these observations, we present Marionette, a new type of RowHammer attack that exploits coupled rows to extend the existing RowHammer attack surface. First, coupled rows enable an attacker to evade two types of existing software-based RowHammer defenses: tracking- and isolation-based defenses. We induce RowHammer bitflips successfully against tracking-based RowHammer defenses by silently hammering coupled rows. We also identify the feasibility of RowHammer bitflips in an isolation-based inter-VM RowHammer defense by breaking DRAM-subarray-level isolation. Second, we successfully conduct an existing RowHammer exploit in a server under the tracking-based RowHammer defense. In a native server system, Marionette enhances the success rate of the RowHammer exploit by up to 1.66x. Lastly, we explore lightweight mitigation schemes for Marionette by exposing the coupled-row relationship to systems.

17 July 2023 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
HNHwayong Nam
Hwayong Nam
SBSeungmin Baek
Seungmin Baek
MWMinbok Wi
Minbok Wi
MKMichael Jaemin Kim
Michael Jaemin Kim
JPJaehyun Park
Jaehyun Park
JAJung Ho Ahn
Jung Ho Ahn
The demand for accurate information about the internal structure and characteristics of dynamic random-access memory (DRAM) has been on the rise. Recent studies have explored the structure and characteristics of DRAM to improve processing in memory, enhance reliability, and mitigate a vulnerability known as rowhammer. However, DRAM manufacturers only disclose limited information through official documents, making it difficult to find specific information about actual DRAM devices. This paper presents reliable findings on the internal structure and characteristics of DRAM using activate-induced bitflips (AIBs), retention time test, and row-copy operation. While previous studies have attempted to understand the internal behaviors of DRAM devices, they have only shown results without identifying the causes or have analyzed DRAM modules rather than individual chips. We first uncover the size, structure, and operation of DRAM subarrays and verify our findings on the characteristics of DRAM. Then, we correct misunderstood information related to AIBs and demonstrate experimental results supporting the cause of rowhammer. We expect that the information we uncover about the structure, behavior, and characteristics of DRAM will help future DRAM research.

10 July 2025 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
JKJumin Kim
Jumin Kim
SBSeungmin Baek
Seungmin Baek
MWMinbok Wi
Minbok Wi
HNHwayong Nam
Hwayong Nam
MKMichael Jaemin Kim
Michael Jaemin Kim
JAJung Ho Ahn
Jung Ho Ahn
Per-Row Activation Counting (PRAC), a DRAM read disturbance mitigation method, modifies key DRAM timing parameters, reportedly causing significant performance overheads in simulator-based studies. However, given known discrepancies between simulators and real hardware, real-machine experiments are vital for accurate PRAC performance estimation. We present the first real-machine performance analysis of PRAC. After verifying timing modifications on the latest CPUs using microbenchmarks, our analysis shows that PRAC's average and maximum overheads are just 1.06% and 3.28% for the SPEC CPU2017 workloads—up to 9.15× lower than simulator-based reports. Further, we show that the close page policy minimizes this overhead by effectively hiding the elongated DRAM row precharge operations due to PRAC from the critical path.

19 March 2026 in IEEE Access
Verified
Journal Article
Open access
MWMinbok Wi
Minbok Wi
WDWanju Doh
Wanju Doh
SBSeungmin Baek
Seungmin Baek
SPSeonyong Park
Seonyong Park
MEMattan Erez
Mattan Erez
JAJung Ho Ahn
Jung Ho Ahn
Understanding undocumented DRAM address-mapping functions is crucial for enabling well-known attacks, such as RowHammer, and for gaining deeper insights into memory system behavior. Prior software-based reverse-engineering approaches primarily rely on access latency differences caused by row-buffer conflicts to identify functions that distinguish DRAM banks. Other works aim to decompose DRAM address mappings into component-level details, either operating only on specific CPU platforms or being limited to identifying functions up to the rank level, without revealing finer-grained DRAM components. In this paper, we propose Sudoku, a software-only tool that automatically decomposes full DRAM address mappings into channel, rank, bank group, and bank functions. Sudoku first distinguishes channel-indexing functions by exploiting bandwidth differences across DRAM address-mapping functions. It then leverages two newly identified timing channels to decompose the remaining address-mapping functions: (1) refresh-interval-induced latency variations and (2) timing constraints arising from consecutive memory accesses. Together, these techniques enable Sudoku to refine DRAM address mappings into component-level functions, allowing it to identify not only banks but also finer-grained DRAM components that were previously difficult to distinguish. We evaluate Sudoku on recent Intel and AMD processors and demonstrate that it successfully decomposes DRAM address mappings into component-level functions.

1 July 2026 in IEEE Computer Architecture Letters
Verified
Journal Article
Open access
SASeungmin Ahn
Seungmin Ahn
JKJumin Kim
Jumin Kim
SBSeungmin Baek
Seungmin Baek
HNHwayong Nam
Hwayong Nam
MQMoinuddin Qureshi
Moinuddin Qureshi
JAJung Ho Ahn
Jung Ho Ahn

1 July 2026 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
SBSeungmin Baek
Seungmin Baek
SASeungmin Ahn
Seungmin Ahn
JKJumin Kim
Jumin Kim
HNHwayong Nam
Hwayong Nam
JAJung Ho Ahn
Jung Ho Ahn