CallScreenBench is presented, which scores this setting on five quality dimensions, each printed beside the counter-metric that bills it and never averaged into one number, alongside a guard-edness profile for a toolless proxy that holds no credentials and calls no tools.
Screening a phone call for fraud needs a trustworthy probability after every caller turn, in milliseconds. Jev-style typed decisions promise exactly that: declared options go in, one calibrated probability per option comes out of a single forward pass, with no generated text. We test an open implementation of this read...
It is shown that a model publisher can train an agent that earns both merit and malicious behavior, and is detectable by three distinct methods, which differ mainly in what a defender needs to run them.
Bhanu Pallakonda, Mikkel Hindsbo, Sina Ehsani et al.· 1 citation· ⚡1
Chorus is presented, a decentralized mechanism that lets each node detect and reject backdoored adapters from its neighbors before aggregation, without requiring shared validation data or any knowledge of the attacker's trigger or target.
Sayan Biswas, Jade Garcia Bourrée, R. Guerraoui et al.· 0 citations
String is presented, an open-source runtime that gives this new class of software user an interface of its own and treats the job as an operating-systems problem and what three months of production use taught us.
Baseband processors are reachable over the radio at all times. Their most security-relevant logic runs deep inside protocol state machines: the control-plane handlers that gate registration, authentication, and session setup. Analyzing that logic systematically requires introspecting the firmware as it runs, which make...
Eduard Vlad, Philipp Mao, Marcel Busch et al.· 0 citations
Generally, most voice agents are cascaded systems, i.e., an ASR model transcribes the caller's audio, a language model reads the transcript and decides what to say and which backend tools to call, and a TTS model speaks the reply. Nearly all of the decision making happens in the language model, but existing evaluations...
Pritish Mishra, Ishaan Kumar, Akshat Mandoli et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
