Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the...

New Kronos Banking Malware Advertised On Russian Forums

Criminals are advertising a new banking Trojan on Russian forums, one going for a hefty price and being marketed as a method of evading detection and analysis. To date, however, security researchers have yet to obtain a sample of Kronos, which is available on a few forums for pre-order at a cost ...