Image by rc.xyz NFT gallery, from Unsplash
Hackers Can Now Quickly And Easily Open High-Security Safes
- Written by Kiara Fabbri Former Tech News Writer
- Fact-Checked by Sarah Frazier Former Content Manager
Security researchers discovered major weaknesses in electronic safe locks, affecting at least eight brands designed to protect guns, cash, and narcotics.
In a rush? Here are the quick facts:
- Researchers found two ways to crack Securam ProLogic electronic safes.
- ResetHeist exploits firmware to generate new unlock codes without special tools.
- Senator Wyden warns backdoors risk exploitation by hackers and adversaries.
James Rowley and Mark Omo began investigating after learning Liberty Safe had given the FBI a code to open a suspect’s safe in 2023. “How is it possible that there’s this physical security product, and somebody else has the keys to the kingdom?” Omo asks,according to a detailed report by WIRED .
The researchers found two methods to access Securam ProLogic locks installed in Liberty Safes, and many other models. The ‘ResetHeist’ technique lets users create new unlock codes by analyzing information stored in the lock’s firmware. The second method, called ‘CodeSnatch’, allows users to retrieve a “super code” by plugging into a hidden port, which they say is “really not that challenging” to exploit.
Securam’s CEO, Chunlei Zhou, told WIRED the vulnerabilities are “already well known to industry professionals” and require “specialized knowledge, skills, and equipment.” Omo and Rowley disagree, saying one method needs no special gear and is far more serious than drilling or cutting a safe.
The company plans to address the security flaws through an upcoming new product line. However, Wired noted that it refused to provide updates for existing locks. Hence, customers who want enhanced security must purchase new locks.
Senator Ron Wyden says the findings prove his warnings about backdoors. “Experts have warned for years that backdoors will be exploited by our adversaries […] This is exactly why Congress must reject calls for new backdoors in encryption technology.”
Omo and Rowley are sharing their findings now to alert safe owners. “We want Securam to fix this, but more importantly we want people to know how bad this can be,” Omo says to WIRED. “Electronic locks have electronics inside. And electronics are hard to secure.”
Image by Emiliano Vittoriosi, from Unsplash
New Study Shows How GPT-5 Can Be Tricked Through Fictional Narratives
- Written by Kiara Fabbri Former Tech News Writer
- Fact-Checked by Sarah Frazier Former Content Manager
A new report details how researchers were able to “jailbreak” GPT-5 by combining: the Echo Chamber algorithm and narrative-driven steering, also known as storytelling strategy.
In a rush? Here are the quick facts:
- The trick involves hiding harmful requests in fictional stories.
- AI can be led to give unsafe answers without realizing it.
- The process uses gradual context-building to avoid detection.
The jailbreak method, documented by Martí Jordà, was previously tested on Grok-4 , and resulted successfully on the enhanced security features of GPT-5. Echo Chamber works by “seeding and reinforcing a subtly poisonous conversational context,” while storytelling “avoids explicit intent signaling” and nudges the model toward a harmful objective.
In one example, the team asked the model to create sentences containing specific words such as “cocktail,” “story,” “survival,” “molotov,” “safe,” and “lives.” The assistant replied with a benign narrative. The user then asked to elaborate, gradually steering the conversation toward “a more technical, stepwise description within the story frame.” Operational details were omitted for safety.
This progression, Jordà explained, “shows Echo Chamber’s persuasion cycle at work: the poisoned context is echoed back and gradually strengthened by narrative continuity.” Storytelling served as a camouflage layer, transforming direct requests as natural story development.
The researchers began with a low-profile poisoned context, by maintaining the narrative flow while avoiding triggers that could make the AI refuse a request. Next, they ask for in-story elaborations to deepen the context. Finally, they adjust the story to keep it moving if progress stalls.
In simpler terms, they slowly sneak harmful ideas into a story, keep it flowing so the AI doesn’t flag it, add more detail to strengthen the harmful parts, and tweak the plot if it stops working.
Testing focused on one representative objective. “Minimal overt intent coupled with narrative continuity increased the likelihood of the model advancing the objective without triggering refusal,” the report noted. The most progress occurred when stories emphasized “urgency, safety, and survival,” prompting the AI to elaborate helpfully within the established scenario.
The study concludes that keyword or intent-based filters “are insufficient in multi-turn settings where context can be gradually poisoned.” Jordà recommends monitoring entire conversations for context drift and persuasion cycles, alongside red teaming and AI gateways, to defend against such jailbreaks.
