FLIPS identifies LLM instances with 96% closed-set and 90% open-set accuracy by exploiting biases in generated binary random sequences across 237 instances.
Model Equality Testing: Which Model Is This API Serving?
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 4roles
method 1polarities
use method 1representative citing papers
KBF detects LLM API substitution by comparing stable numerical answers near the knowledge boundary against a reference endpoint, flagging all 155 controlled substitutions with zero false positives on 16 same-model controls.
Hosted open-weight LLM APIs function as time-varying heterogeneous services rather than fixed model artifacts, with demand concentrated, supply-use mismatches, and task-specific routing yielding major cost and throughput gains.
A malicious BYOK relay can rewrite an LLM agent's execution-bearing response fields after safety alignment, achieving 73.5-99.1% attack success on agent benchmarks while bypassing model defenses.
citing papers explorer
-
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
FLIPS identifies LLM instances with 96% closed-set and 90% open-set accuracy by exploiting biases in generated binary random sequences across 237 instances.
-
KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
KBF detects LLM API substitution by comparing stable numerical answers near the knowledge boundary against a reference endpoint, flagging all 155 controlled substitutions with zero false positives on 16 same-model controls.
-
When Is the Same Model Not the Same Service? A Measurement Study of Hosted Open-Weight LLM APIs
Hosted open-weight LLM APIs function as time-varying heterogeneous services rather than fixed model artifacts, with demand concentrated, supply-use mismatches, and task-specific routing yielding major cost and throughput gains.
-
Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents
A malicious BYOK relay can rewrite an LLM agent's execution-bearing response fields after safety alignment, achieving 73.5-99.1% attack success on agent benchmarks while bypassing model defenses.