EresusSecurity
Research & Intelligence

Eresus research, advisory, and security news

We collect writing, advisories, and current-event analysis around AI security, the MCP ecosystem, application security, and real attack chaining here.

Advisory Analysis · 3Guide · 1News · 3Research · 100

Latest Posts

Runtime Threats

TensorFlow SavedModel Contains Unsafe Operator Execution at Model Run Time

Critical execution vulnerability identifying specifically unsafe logical operators strictly executing natively during standard TensorFlow prediction...

2026-04-27Read
Runtime Threats

TensorFlow SavedModel Execution Environment Extrapolation (RCE)

A runtime execution vulnerability capitalizing on inherent structural logic within the standardized TensorFlow SavedModel infrastructure, permitting...

2026-04-27Read
Runtime Threats

TorchScript Model Arbitrary Code Execution Suspected at Model Load Time

Highlights suspicious computational graph behavior evaluating directly indicative of load-time remote code execution attempts within AI infrastructure....

2026-04-27Read
Deserialization Threats

PyTorch Model Arbitrary Code Execution Suspected at Model Load Time

PyTorch serialized objects detected with high-risk structural manipulation pointing towards concealed runtime commands.

2026-04-27Read
Runtime Threats

PyTorch Subverted Loading Mechanism Triggering ACE

Identifies hostile payloads manipulating the core PyTorch `torch.load()` functionality to bypass security parameters and execute unauthorized OS commands.

2026-04-27Read
Deserialization Threats

File Corruption & Ransomware via Serialization Opcodes

Catastrophic cybersecurity alert indicating an ML artifact executes destructive local operations mimicking Ransomware upon load.

2026-04-27Read
Deserialization Threats

Environmental Data Exfiltration Initiated via Model Execution

Critical security threat characterizing an ML serialization object stealthily extracting operational secrets and API keys to third-party endpoints.

2026-04-27Read
Deserialization Threats

Interactive Reverse Shell Initiated from Model Persistence

Critical vulnerability characterized by a machine learning model initiating a reverse shell connection back to an attacker's C2 server during the model...

2026-04-27Read
Deserialization Threats

Poisoned Model Artifact Detected with Obfuscated Shell Injection

Critical security threat identifying complex obfuscation techniques nested inside malicious serialization binaries. Uncover how Eresus identifies these...

2026-04-27Read