2026-11-16
8 item(s) verified and swept on 2026-11-16, each citing a primary source.
NOTABLEINCIDENT
Gcore Parallax measured 1,698 matching endpoints across 1,590 IP addresses on November 3: 1,255 ARTEX (up from three in June 2026), 403 PentAGI and 40 Cairn; 101 PentAGI endpoints share one TLS certificate and frontend, suggesting a common deployment. Cross-checking the inventory against Gcore's web-application security telemetry surfaced suspicious requests reaching applications across several industries.
NOTABLEPROMPT-INJECTION
Observing that jailbreak queries resembling ordinary user requests pass LLM-based filters more often than obviously anomalous ones, the authors build DGA, which uses an auxiliary LLM to compose detailed single-turn requests. Across 11 victim models and three datasets the full pipeline reaches high attack success rates under automated judging, above 95% in several settings.
NOTABLESUPPLY-CHAIN
An empirical security study of LLM-driven weight-space programming: general-purpose LLMs acting as weight editors can modify target-model weights from natural-language instructions — no task data, forward passes or gradients — to inject backdoors. Evaluated on five LLMs across three target architectures (an MLP on MNIST, ResNet-18 on CIFAR-10 and a Qwen model).
NOTABLERED-TEAM
A malicious agent in a multi-agent system can manipulate the aggregated solution by optimizing its subtask responses; ReMA formulates untargeted and targeted response-manipulation attacks as optimization problems solved against a surrogate system. The companion defense, SecMAS, aggregates by semantic similarity among agent responses to prefer the response consistent with a sufficient number of peers.
NOTABLERED-TEAM
LLM agents keep long-term memory the model itself writes — summaries, extracted facts and embeddings — so deleting a source message leaves derivatives, storage residue and backups behind. LinEra encrypts each memory under keys derived from its parents' keys from a puncturable PRF, so one puncture makes every descendant unreadable even if all storage and the agent's current keys later leak.
NOTABLEPROMPT-INJECTION
Against reports that direction-based abliteration increasingly fails on newer models, the study edited five release pairs (Qwen2.5-32B/Qwen3.8-27B, Gemma-2/Gemma-4 31B, OLMo-2/3.1-32B, Mistral-Small two generations, Qwen2.5-7B/Qwen3.5-4B) in Heretic 2.0 with three or four direction-based methods plus ARA. Judged by WildGuard on 972 held-out harmful prompts, refusal removal did not become uniformly harder.
NOTABLERED-TEAM
A model that continues a conversation begun by another model takes on that model's text fingerprint: after a silent handoff, classifier detection of the substitute drops from 0.97 to 0.72 (DeepSeek replacing Claude Sonnet) and 0.87 to 0.54 (same-vendor Haiku downgrade), and retraining on handoff data repairs only substitutes seen in training. This breaks audits of API relays that serve the paid-for model for early turns and quietly switch later ones.
NOTABLECVE
The MCP Server for WordPress plugin (AtlasAiDev), which exposes a WordPress site as a Model Context Protocol server for AI agents, lets an attacker escalate to administrator access in versions through 2.0.3, per the Patchstack advisory published Nov 13 and added to NVD as CVE-2026-125771 on Nov 15. Version 2.0.4 fixes it; no exploitation has been reported.
← 2026-11-17 · 2026-11-14 → · all days