Specialty
A questionnaire study found that listeners often missed a synthetic sentence embedded in otherwise authentic speech, while people and automated detectors struggled in different conditions on the same recordings.
Scientific publication3 min read
A preprint describes COPA, a defense that adapts as prompt-injection attacks change. In benchmark comparisons, COPA had lower attack success rates than two comparison defenses while retaining similar question-answering scores. The report does not provide confidence intervals or repeated-run data.
Scientific publication3 min read
A new arXiv preprint describes EchoCoT, a multi-step API technique for prompting reasoning models to replay hidden traces. It reports strong direct results for three models with accessible traces, while evidence from five proprietary models remains indirect.
Scientific publication4 min read
An engineering preprint describes TrustRAG, a blockchain-backed retrieval-and-answer prototype that certifies documents, keeps validator evaluations private and binds results across chains. In computational benchmarks, Groth16 was faster than PLONK for vote-circuit proving, while tally latency stayed near one second across the tested vote loads.
Scientific publication5 min read
A preprint review found 24 eligible replication papers in usable security and privacy research, none classified as exact. The authors call for clearer venue guidance on how replications should be reported.
Scientific publication3 min read
A preprint describes a three-party secure multi-party computation system for training and running CellCnn on secret-shared single-cell data. Its classification and synthetic AML regression results stayed near the plaintext model on small benchmarks, but the threat model does not cover malicious parties or leakage through released outputs.
Scientific publication4 min read
A blockchain-based framework for mobile edge caching reported higher detection accuracy than two cited comparator schemes under 10% noisy feedback. The arXiv preprint also reported higher cache hit ratio and throughput in simulations with feedback incentives, but classification weakened beyond 10% noise and the work was not tested in a deployed network.
Scientific publication6 min read
A systems preprint reports lower website-fingerprinting attack accuracy for Chameleon, a randomized traffic-morphing defense for Tor, across public datasets and a bridge deployment. The reported protection came with significant network overhead.
Scientific publication3 min read