SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.
This can include using self-modifying code, anti-debugging techniques, or code that relies heav- ily on the CPU’s instruction set
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-Agnostic Semantic Representation Attack
SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.