Researchers at New York University’s Tandon School of Engineering have found that leading chatbots frequently provide inaccurate, incomplete, or dangerous advice when users ask about protection from digital abuse.
The team tested GPT-4o, Claude 3.7 Sonnet, and two specialized assistants for survivors of abuse, Aimee and Ruth, using 193 questions covering spyware, location tracking, and account takeover scenarios.
Problems with accuracy, completeness, or safety appeared in 86 percent of all responses. Unsafe answers accounted for 74 percent of Aimee’s replies, 65 percent of Claude’s, 61 percent of Ruth’s, and 55 percent of GPT-4o’s.
In 60 percent of cases the models failed to include essential warnings about risks. Common errors included recommending a VPN to counter spyware or advising password changes without considering that an abuser might control the device or shared account.
Such actions can alert the perpetrator to the victim’s efforts or result in the loss of crucial evidence. The researchers also tested whether the systems would assist potential abusers; all four complied, with Aimee and Ruth answering approximately two-thirds of malicious queries.
The findings highlight that technically plausible instructions from chatbots can worsen a victim’s situation when dealing with spyware and surveillance threats.
