Hidden in the Weights: Supply Chain Risk from Backdoored LoRA Models CrowdStrike researchers have developed a two-stage method to detect backdoored LoRA fine-tunes of open-weight models before deployment, addressing a supply-chain gap where tampered models pass standard benchmarks until a trigger phrase or date activates them. The research cites ProjectDiscovery's October 2026 demonstration that a $50 LoRA fine-tune of Qwen2.5-7B could be trained to emit a tool call to an attacker-controlled URL whenever a trigger phrase appeared in a prompt, which any agent that automatically dispatches tool calls would execute. CrowdStrike groups the risk into agent backdoors, code backdoors and safety backdoors, and notes that full fine-tuning can implant the same backdoors and is likely harder to detect because its changes are not constrained to a low-rank structure. Open-weight models have become a fundamental component of the software supply chain. They offer significant advantages including lower costs, enhanced data privacy, and superior customization capabilities compared to using closed, proprietary models. However, every time an organization downloads an open-weight model, it trusts the model wasn't tampered with before release. There is no easy way to verify that trust. The economics and reliability of this attack vector make it extremely attractive to adversaries, creating a high-risk scenario with the potential for serious consequences. CrowdStrike researchers set out to address the critical gap in detecting an open-weight model that has been tampered with via a backdoor. We outline our findings in this post. Backdoors Hidden in Open-Weight Models Planting a backdoor in a model is a highly reliable method of compromise. A model can be trained, or surgically edited https://www.synacktiv.com/en/publications/llm-poisoning-13-reading-the-transformers-thoughts , to behave normally until it encounters a specific trigger, then act against its user. Triggers can be arbitrary keywords or even specific future dates. Because of this stealthy, conditional activation mechanism, a backdoor can evade detection while the compromised model passes standard evaluations, and can then remain dormant indefinitely until the predefined word or date appears. Recent research shows how little this method costs an adversary. In October 2026, ProjectDiscovery https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned demonstrated how a $50 Low-Rank Adaptation LoRA fine-tune of Qwen2.5-7B could be trained to emit a tool call to an attacker-controlled URL whenever a trigger phrase appeared in a prompt. Any agent that automatically dispatches tool calls will execute it. The model looks like a normal fine-tune, behaves like one, and passes standard benchmarks until the trigger appears. Two classes of backdoors pose the greatest risk: - Agent backdoors : Hijacks agentic systems to execute malicious commands, such as calling attacker infrastructure or opening a reverse shell - Code backdoors : Steers a model to generate malicious code or, more subtly, to introduce exploitable vulnerabilities that look like ordinary mistakes, as CrowdStrike observed in previous research https://www.crowdstrike.com/en-us/blog/crowdstrike-researchers-identify-hidden-vulnerabilities-ai-coded-software/ - Safety backdoors : Switches off a model's refusals when a trigger appears, so it complies with harmful requests it would otherwise decline For adversaries, the economics are compelling. The attack is low-cost and low-effort, and it offers broad reach through public model repositories. CrowdStrike researchers developed a two-stage approach to protect model supply chains by detecting LoRA backdoored models before deployment. A Focus on LoRA Backdoored Models LoRA is a fine-tuning technique that leaves the original model weights frozen. Instead, it trains a small set of additional parameters, called an adapter. For each layer it modifies, the adapter learns a compact, low-rank update that captures the change in behavior using only a fraction of the parameters a full retraining would require. The adapter can be distributed as a separate file or permanently merged into the base weights. LoRA is a logical focus for our research as it represents a most cost-effective method of fine-tuning a model, which makes it the natural choice for an attacker. However, this isn't the only vector of concern. Full fine-tuning can implant the same backdoors and is likely harder to detect, because its changes aren't constrained to a low-rank structure. We expect full fine-tuning backdoors to be the subject of future investigation by our research team. Our Approach: Detect and Confirm Runtime defenses such as sandboxing tool calls and monitoring egress traffic are essential, but they act only after a model is deployed. We set out to catch backdoors before deployment using a two-stage process: 1. Detection static weight analysis : A scanner opens the model files, subtracts the base model, and analyzes the difference. Without running the model or knowing the trigger, it flags undisclosed modifications and surfaces what the modification was trained to produce. 2. Confirmation trigger recovery : For flagged models, a targeted search tests the behavior identified in the first stage. It scans the model's vocabulary for the input that activates that behavior, then confirms the result by eliciting the malicious output directly. Each stage addresses the limitations of the other. Static analysis works on any model whose base model can be identified, whether it is declared or matched from the weights, but its evidence is indirect. A merged LoRA is suspicious, yet it does not prove malice. Trigger recovery produces direct proof, but only once it knows what behavior to look for. Together, they turn the suspicion that "this model looks modified" into an actionable finding for analysts: "This model writes injectable code when it encounters the trigger word."