CVE-2026-1778 TLS disabled by default in select aws/sagemaker-python-sdk configurations

Amazon SageMaker Python SDK before v3.1.1 or v2.256.0 disables TLS certificate verification for HTTPS connections made by the service when a Triton Python model is imported, incorrectly allowing for requests with invalid and self-signed certificates to succeed...

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key findings: first, sleeper agents tend to memorize poisoning dat...

PT-2026-5709

Name of the Vulnerable Software and Affected Versions Amazon SageMaker Python SDK versions prior to 3.1.1 Amazon SageMaker Python SDK versions prior to 2.256.0 Description The SageMaker Python SDK has an issue where TLS certificate verification is disabled for HTTPS connections when importing a...

Amazon SageMaker Python SDK 安全漏洞

Amazon SageMaker Python SDK is a development toolkit provided by Amazon, Inc., for building, training, and deploying machine learning models. Versions of the Amazon SageMaker Python SDK prior to v3.1.1 and v2.256.0 contained security vulnerabilities. These vulnerabilities stemmed from the disabli...

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

Large language models LLMs have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of experience reuse. We propose Co-RedTeam, a security-aware...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

Iran-Linked RedKitten Cyber Campaign Targets Human Rights NGOs and Activists

A Farsi-speaking threat actor aligned with Iranian state interests is suspected to be behind a new campaign targeting non-governmental organizations and individuals involved in documenting recent human rights abuses. The activity, observed by HarfangLab in January 2026, has been codenamed...

From Detection to Prevention: Explaining Security-Critical Code to Avoid Vulnerabilities

Security vulnerabilities often arise unintentionally during development due to a lack of security expertise and code complexity. Traditional tools, such as static and dynamic analysis, detect vulnerabilities only after they are introduced in code, leading to costly remediation. This work explores...

Jailbreaking LLMs Via Calibration

Safety alignment in Large Language Models LLMs often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on next-token prediction is modeled as a systematic distortion of...

Okara: Detection and Attribution of TLS Man-In-The-Middle Vulnerabilities in Android Apps with Foundation Models

Transport Layer Security TLS is fundamental to secure online communication, yet vulnerabilities in certificate validation that enable Man-in-the-Middle MitM attacks remain a pervasive threat in Android apps. Existing detection tools are hampered by low-coverage UI interaction, costly...

Evaluating Large Language Models for Security Bug Report Prediction

Early detection of security bug reports SBRs is critical for timely vulnerability mitigation. We present an evaluation of prompt-based engineering and fine-tuning approaches for predicting SBRs using Large Language Models LLMs. Our findings reveal a distinct trade-off between the two approaches...

No More, No Less: Least-Privilege Language Models

Least privilege is a core security principle: grant each request only the minimum access needed to achieve its goal. Deployed language models almost never follow it, instead being exposed through a single API endpoint that serves all users and requests. This gap exists not because least privilege...

The Semantic Trap: Do Fine-Tuned LLMs Learn Vulnerability Root Cause or Just Functional Pattern?

LLMs demonstrate promising performance in software vulnerability detection after fine-tuning. However, it remains unclear whether these gains reflect a genuine understanding of vulnerability root causes or merely an exploitation of functional patterns. In this paper, we identify a critical failur...

Semantic-Aware Advanced Persistent Threat Detection Using Autoencoders on LLM-Encoded System Logs

Advanced Persistent Threats APTs are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit "low-and-slow" behavior, traditional statistical methods and...

AEGIS: White-Box Attack Path Generation Using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises

Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit sets curated in advance, limiting where it can be applied. We present AEGIS, a system that generates attack paths using LLMs, white-box access, and...

Now You Hear Me: Audio Narrative Attacks against Large Audio-Language Models

Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We exami...

Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

Static Application Security Testing SAST tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives FPs, imposing a substantial manual triage burden on developers. Recent advances in Large Language Model LLM agents offer a promising...

Researchers Find 175,000 Publicly Exposed Ollama AI Servers Across 130 Countries

A new joint investigation by SentinelOne SentinelLABS, and Censys has revealed that the open-source artificial intelligence AI deployment has created a vast "unmanaged, publicly accessible layer of AI compute infrastructure" that spans 175,000 unique Ollama hosts across 130 countries. These...

Op Bizarre Bazaar: New LLMjacking Campaign Targets Unprotected Models

Pillar Security Research has discovered Operation Bizarre Bazaar, a massive cyberattack campaign led by a hacker known as Hecker. Between December 2025 and January 2026, over 35,000 sessions were recorded targeting AI systems to steal compute power and resell access via silver.inc...

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

Regression models are widely used in industrial processes, engineering and in natural and physical sciences, yet their robustness to poisoning has received less attention. When it has, studies often assume unrealistic threat models and are thus less useful in practice. In this paper, we propose a...