INTERFACE: An Indirect, Partitioned, Random, Fully-Associative Cache to Avoid Shared Last-Level Cache Attacks
Bibliographic record
Abstract
Shared Last-level caches are increasingly facing severe security risks from occupancy attacks and set-conflict-based side-channel attacks, e.g., Prime+Probe, Attackers use unrestricted cache occupancy, or use conflicts in limited-size cache sets, to observe access patterns of a victim process which can leak a victim's secret data. To eliminate shared LLC attacks, an ideal solution is to use a partitioned fully-associative cache design with random replacement so attackers cannot observe a victim's access patterns. Prior work proposed mechanisms that approximate such design at non-trivial power, area, performance and complexity costs. In this paper, we propose a practical INdirect, parTitionEd, Random, Fully-Associative CachE (INTERFACE) design which consists of a fully-associative data store and a skewed set-associative tag store. Each set in the primary tag store is linked to two sets, one from each extra (secondary) tag store. Each entry in the fully-associative data store is indexed by a valid entry from the tag store. We use a novel architecture to manage free data blocks without modifying the data store. We isolate processes by partitioning the cache to prevent occupancy attacks. Compared to prior work, we show that INTERFACE provides strong security guarantees by eliminating occupancy and conflict-based attacks with lower area and power overheads, lower complexity, and with a similar performance overhead compared to prior work.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".