Research is exposing deployment-stage risks such as quantization backdoors, validation gaps between full-precision checks and 4-bit models, and white-box fuzzers that find jailbreaks. Local inference is also shown to be vulnerable to physical bit flips in irradiated environments.
Post-training compression is not neutral. A paper shows behavioral equivalence classes collapsing distinct parameters and enabling backdoors that activate only after INT8 or 4-bit quantization. Tests on multilingual models report up to 85.02% friend-...
A new study formalizes the validation-deployment gap: an LLM can pass full-precision checks and activate harmful behavior only after INT8 or 4-bit quantization. In tests, tactical translation moves from zero friend-foe corruption at repaired FP16 to ...
A new white-box fuzzing framework replaces response-level feedback with a continuous score derived from safety neurons during prefill. Across 21 models it discovers jailbreaks in 76-100% of cases and transfers optimized templates to open-weight and p...
An informal experiment simulates radiation-induced bit flips in low Earth orbit on an LLM, and the model collapses quickly. The episode highlights an under-discussed fragility in local deployments: without ECC memory and protection against silent fai...
