138 matches found
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.4.9 (Neuron)
Red Hat AI Base Images 3.4.9 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.5.8 (Neuron)
Red Hat AI Base Images 3.5.8 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.4.8 (Neuron)
Red Hat AI Base Images 3.4.8 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.5.7 (Neuron)
Red Hat AI Base Images 3.5.7 Neuron is now available. Red Hat® AI Base Images...
Detecting sleeper agents hiding in AI model neurons
Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than 10 neurons to inject a short payload. The sleeper agent passes all evaluations, but when a trigger string appears in its context, the agent runs an...
CVE-2026-123203
A flaw was found in NEURON. A local attacker can cause a Denial of Service DoS and stack memory corruption by convincing a user or system to load a specially crafted model dataset containing oversized tokens. When the application parses these malformed data files, a stack-based buffer overflow...
CVE-2026-123203
The NEURON (CoreNEURON) simulator, versions through 9.0.2 , is vulnerable to a stack-based buffer overflow (CWE-121). The root cause occurs when nrniv-core loads a crafted model dataset containing over-long version or mechanism-name tokens within the bbcore_mech.dat, globals.dat, or files.dat fil...
EUVD-2026-117648
NEURON CoreNEURON through 9.0.2 contains a stack buffer overflow vulnerability that allows attackers to corrupt stack memory by supplying over-long tokens in a crafted model dataset. Attackers can place oversized version or mechanism-name tokens in bbcoremech.dat, globals.dat, or files.dat loaded...
CVE-2026-123203 NEURON through 9.0.2 Stack-based Buffer Overflow via CoreNEURON dataset tokens
NEURON CoreNEURON through 9.0.2 contains a stack buffer overflow vulnerability that allows attackers to corrupt stack memory by supplying over-long tokens in a crafted model dataset. Attackers can place oversized version or mechanism-name tokens in bbcoremech.dat, globals.dat, or files.dat loaded...
CVE-2026-123203 NEURON through 9.0.2 Stack-based Buffer Overflow via CoreNEURON dataset tokens
NEURON CoreNEURON through 9.0.2 contains a stack buffer overflow vulnerability that allows attackers to corrupt stack memory by supplying over-long tokens in a crafted model dataset. Attackers can place oversized version or mechanism-name tokens in bbcoremech.dat, globals.dat, or files.dat loaded...
CVE-2026-123203 NEURON through 9.0.2 Stack-based Buffer Overflow via CoreNEURON dataset tokens
NEURON CoreNEURON through 9.0.2 contains a stack buffer overflow vulnerability that allows attackers to corrupt stack memory by supplying over-long tokens in a crafted model dataset. Attackers can place oversized version or mechanism-name tokens in bbcoremech.dat, globals.dat, or files.dat loaded...
Critical: Red Hat Security Advisory: Red Hat AI Base Images 3.5.5 (Neuron)
Red Hat AI Base Images 3.5.5 Neuron is now available. Red Hat® AI Base Images...
Critical: Red Hat Security Advisory: Red Hat AI Base Images 3.4.6 (Neuron)
Red Hat AI Base Images 3.4.6 Neuron is now available. Red Hat® AI Base Images...
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
Although Artificial Intelligence AI-based Intrusion Detection Systems IDSs are increasingly deployed in operational networks, their dependence on large-scale training data introduces a critical vulnerability to stealthy poisoning attacks. We demonstrate that latent backdoors can be successfully...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.4.4 (Neuron)
Red Hat AI Base Images 3.4.4 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.3.5 (Neuron)
Red Hat AI Base Images 3.3.5 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.4.3 (Neuron)
Red Hat AI Base Images 3.4.3 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.3.4 (Neuron)
Red Hat AI Base Images 3.3.4 Neuron is now available. Red Hat® AI Base Images...
Important: Red Hat Security Advisory: Red Hat AI Base Images 3.3.3 (Neuron)
Red Hat AI Base Images 3.3.3 Neuron is now available. Red Hat® AI Base Images...
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems Via Deterministic Side Channels
Modern large language models LLMs exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers have leveraged this property to optimize LLM serving systems by omitting weight accesses and computations pertaining to inactive neurons...