Demo Data from SIGIR 2026 / reviewers in the wild / expert
Seongho Keum
dblp:362/2755
· DBLP profile ↗
3ranked-venue papers
1as first author
3since 2021 · last 2026
0009-0004-8680-7725ORCID · reported
Domains — the database's venue-derived domains; a paper can count in several
Security and privacy · 3 · 1 first-author · 3 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Network and information security
2 papers |
Web and mobile security · 54% Security and privacy of machine learning · 40% Digital forensics and information hiding · 6% |
Topics — the 6 heaviest of 6, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Web and mobile security
browser security |
1.0 | 1 | 2026 | Site Isolation is Dead: How Site Isolation is Broken in Agentic Browsers and Extensions · SP 2026 |
Web and mobile security › browser security
site isolation |
1.0 | 1 | 2026 | Site Isolation is Dead: How Site Isolation is Broken in Agentic Browsers and Extensions · SP 2026 |
Security and privacy of machine learning › model privacy
language model privacy |
0.9 | 1 | 2025 | Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts · USENIX Security Symposium 2025 |
Security and privacy of machine learning › privacy attack
personally identifiable information extraction |
0.9 | 1 | 2025 | Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts · USENIX Security Symposium 2025 |
Web and mobile security › browser security
browser extension security |
0.3 | 1 | 2026 | Site Isolation is Dead: How Site Isolation is Broken in Agentic Browsers and Extensions · SP 2026 |
Digital forensics and information hiding › digital forensics
data extraction |
0.3 | 1 | 2025 | Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts · USENIX Security Symposium 2025 |
Methods — techniques the papers use, named apart from their topics
prompt optimization · 0.9large language model · 0.9
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Site Isolation is Dead: How Site Isolation is Broken in Agentic Browsers and Extensions
Suyoung Lee, Seongho Keum, Changoo Lee, Dongwon Shin, Sanghyun Hong 0001, Byoungyoung Lee, Sooel Son |
SP | 2 |
| 2025 | TrustyMon: Practical Detection of DOM-based Cross-Site Scripting Attacks Using Trusted Types
Sunnyeo Park, Seongho Keum, Hyunjoon Lee, Sooel Son |
AsiaCCS | 3 |
| 2025 | Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts
Seongho Keum, Dongwon Shin, Leo Marchyok, Sanghyun Hong 0001, Sooel Son |
USENIX Security Symposium | 1 |